Method for training positioning model, terminal device, and network device

Abstract

A method for training a positioning model, a terminal device, and a network device are provided. The method for training a positioning model comprises: a terminal device sends first data to a network device. The first data is used for determining second data, and the first data and the second data are training data of a positioning model. The positioning model is used for positioning the terminal device which is within a target positioning region. The target positioning region comprises a first grid unit, and the first data is a measurement result of an acquired reference signal when the terminal device is located in the first grid unit.

Description

Method for training positioning model, terminal device and network device Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to a method for training a positioning model, a terminal device, and a network device. Background Art

[0002] Fingerprint database positioning technology is a commonly used indoor positioning method. To achieve high positioning accuracy, fingerprint database positioning technology usually requires collecting a large amount of fingerprint data to build a fingerprint database, which consumes a lot of time and cost.

[0003] Summary of the Invention

[0004] The present application provides a method for training a positioning model, a terminal device, and a network device. The following introduces various aspects of the present application.

[0005] In a first aspect, a method for training a positioning model is provided, comprising: a terminal device sending first data to a network device, the first data being used to determine second data, and the first data and the second data being training data of a positioning model, the positioning model being used to locate the terminal device within a target positioning area; wherein the target positioning area includes a first grid unit, and the first data is a measurement result of a reference signal obtained when the terminal device is located in the first grid unit.

[0006] In some embodiments, the second data is obtained by random sampling within the distribution range of the first data, and / or the second data is obtained by sampling within the distribution range of the first data based on a probability value.

[0007] In some embodiments, the distribution characteristics of the first data are determined based on the distribution characteristics of third data, where the third data is a reference signal measurement result of a reference area, and the reference area is of the same type as the target positioning area.

[0008] In some embodiments, the amount of the first data is determined based on a data distribution characteristic of the third data.

[0009] In some embodiments, part or all of the second data is tagged with a location.

[0010] In some embodiments, the location tag corresponding to the second data is a randomly generated location coordinate within the first grid unit.

[0011] In some embodiments, the output result of the positioning model is the position coordinates and the position information of the first grid unit, or the position information of the first grid unit.

[0012] In some embodiments, the distribution characteristics of the first data include that the first data obeys a Gaussian distribution, and an expression of the joint Gaussian distribution of the first grid cells is determined based on a mean matrix and a standard deviation matrix.

[0013] In a second aspect, a method for training a positioning model is provided, including: a network device receives first data sent by a terminal device, the first data is used to determine second data, and the first data and the second data are training data of a positioning model, and the positioning model is used to locate the terminal device in a target positioning area; wherein the target positioning area includes a first grid unit, and the first data is a measurement result of a reference signal obtained when the terminal device is located in the first grid unit.

[0014] In some embodiments, the second data is obtained by random sampling within the distribution range of the first data, and / or the second data is obtained by sampling within the distribution range of the first data based on a probability value.

[0015] In some embodiments, the distribution characteristics of the first data are determined based on the distribution characteristics of third data, where the third data is a reference signal measurement result of a reference area, and the reference area is of the same type as the target positioning area.

[0016] In some embodiments, the amount of the first data is determined based on a data distribution characteristic of the third data.

[0017] In some embodiments, part or all of the second data is tagged with a location.

[0018] In some embodiments, the location tag corresponding to the second data is a randomly generated location coordinate within the first grid unit.

[0019] In some embodiments, the output result of the positioning model is the position coordinates and the position information of the first grid unit, or the position information of the first grid unit.

[0020] In some embodiments, the distribution characteristics of the first data include that the first data obeys a Gaussian distribution, and an expression of the joint Gaussian distribution of the first grid cells is determined based on a mean matrix and a standard deviation matrix.

[0021] According to a third aspect, a terminal device is provided, comprising: a sending unit for sending first data to a network device, wherein the first data is used to determine second data, and the first data and the second data are training data of a positioning model, and the positioning model is used to locate the terminal device within a target positioning area; wherein the target positioning area includes a first grid unit, and the first data is a measurement result of a reference signal obtained when the terminal device is located in the first grid unit.

[0022] In some embodiments, the second data is obtained by random sampling within the distribution range of the first data, and / or the second data is obtained by sampling within the distribution range of the first data based on a probability value.

[0023] In some embodiments, the distribution characteristics of the first data are determined based on the distribution characteristics of third data, where the third data is a reference signal measurement result of a reference area, and the reference area is of the same type as the target positioning area.

[0024] In some embodiments, the amount of the first data is determined based on a data distribution characteristic of the third data.

[0025] In some embodiments, part or all of the second data is tagged with a location.

[0026] In some embodiments, the location tag corresponding to the second data is a randomly generated location coordinate within the first grid unit.

[0027] In some embodiments, the output result of the positioning model is the position coordinates and the position information of the first grid unit, or the position information of the first grid unit.

[0028] In some embodiments, the distribution characteristics of the first data include that the first data obeys a Gaussian distribution, and an expression of the joint Gaussian distribution of the first grid cells is determined based on a mean matrix and a standard deviation matrix.

[0029] In a fourth aspect, a network device is provided, comprising: a receiving unit for receiving first data sent by a terminal device, the first data being used to determine second data, and the first data and the second data being training data of a positioning model, and the positioning model being used to locate the terminal device within a target positioning area; wherein the target positioning area includes a first grid unit, and the first data is a measurement result of a reference signal obtained when the terminal device is located in the first grid unit.

[0030] In some embodiments, the second data is obtained by random sampling within the distribution range of the first data, and / or the second data is obtained by sampling within the distribution range of the first data based on a probability value.

[0031] In some embodiments, the distribution characteristics of the first data are determined based on the distribution characteristics of third data, where the third data is a reference signal measurement result of a reference area, and the reference area is of the same type as the target positioning area.

[0032] In some embodiments, the amount of the first data is determined based on a data distribution characteristic of the third data.

[0033] In some embodiments, part or all of the second data is tagged with a location.

[0034] In some embodiments, the location tag corresponding to the second data is a randomly generated location coordinate within the first grid unit.

[0035] In some embodiments, the output result of the positioning model is the position coordinates and the position information of the first grid unit, or the position information of the first grid unit.

[0036] In some embodiments, the distribution characteristics of the first data include that the first data obeys a Gaussian distribution, and an expression of the joint Gaussian distribution of the first grid cells is determined based on a mean matrix and a standard deviation matrix.

[0037] In a fifth aspect, a terminal device is provided, comprising a processor and a memory, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the terminal device executes part or all of the steps in the method of the first aspect.

[0038] In a sixth aspect, a network device is provided, comprising a processor, a memory, and a transceiver, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the network device executes part or all of the steps in the method of the second aspect.

[0039] In a seventh aspect, an embodiment of the present application provides a communication system, which includes the above-mentioned terminal device and / or network device. In another possible design, the system may also include other devices that interact with the terminal device or network device in the solution provided in the embodiment of the present application.

[0040] In an eighth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program enables a terminal device and / or a network device to execute part or all of the steps in the methods of the above aspects.

[0041] In a ninth aspect, embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a terminal device and / or a network device to perform some or all of the steps of the methods described in each of the above aspects. In some implementations, the computer program product may be a software installation package.

[0042] In the tenth aspect, an embodiment of the present application provides a chip, which includes a memory and a processor. The processor can call and run a computer program from the memory to implement some or all of the steps described in the methods of the above aspects.

[0043] After research, the applicant found that fingerprint data within a certain area has a certain correlation, or that many collected fingerprint data are actually similar or redundant. Therefore, such intensive data collection is not necessary. Based on this, the method provided in the embodiment of the present application can obtain some extended fingerprint data (i.e., second data) based on the actual collected fingerprint data (i.e., first data), and use the first data and second data to train the positioning model. In this way, in the process of establishing a fingerprint library, the amount of fingerprint data collected can be reduced, thereby helping to reduce the time and resource consumption of establishing the fingerprint library. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] FIG1 is a schematic diagram of a wireless communication system used in an embodiment of the present application.

[0045] FIG. 2 shows an example diagram of line-of-sight and non-line-of-sight.

[0046] FIG3 is a schematic diagram of the fingerprint data location in a high-density indoor factory scene.

[0047] FIG. 4 is a schematic diagram of a Gaussian distribution curve of fingerprint data of the grid unit 330 in FIG. 3 .

[0048] FIG. 5 is a schematic diagram illustrating the discreteness of fingerprint data of the grid unit 330 in FIG. 3 .

[0049] FIG6 is a schematic flowchart of a method for training a positioning model provided in an embodiment of the present application.

[0050] FIG7A is an example diagram of obtaining enhanced fingerprint data provided by an embodiment of the present application.

[0051] FIG7B is an example diagram of a training positioning model provided in an embodiment of the present application.

[0052] FIG7C is a flow chart of a method for using a positioning model provided in an embodiment of the present application.

[0053] FIG8 is a schematic structural diagram of a terminal device provided in an embodiment of the present application.

[0054] FIG9 is a schematic structural diagram of a network device provided in an embodiment of the present application.

[0055] FIG10 is a schematic structural diagram of a device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The technical solution in this application will be described below with reference to the accompanying drawings.

[0057] Communication System

[0058] Figure 1 illustrates a wireless communication system 100 used in an embodiment of the present application. The wireless communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 may provide communication coverage for a specific geographic area and may communicate with the terminal device 120 within the coverage area.

[0059] FIG1 exemplarily shows a network device and two terminals. Optionally, the wireless communication system 100 may include multiple network devices and each network device may include other numbers of terminal devices within its coverage area, which is not limited in the embodiments of the present application.

[0060] Optionally, the wireless communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0061] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: fifth generation (5G) system or new radio (NR), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), etc. The technical solutions provided in this application can also be applied to future communication systems, such as the sixth generation mobile communication system, satellite communication system, etc.

[0062] The terminal device in the embodiments of the present application may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device. The terminal device in the embodiments of the present application may refer to a device that provides voice and / or data connectivity to a user and can be used to connect people, objects and machines, such as a handheld device with wireless connection function, a vehicle-mounted device, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity that provides sidelink signals between UEs in vehicle-to-everything (V2X) or device-to-device (D2D). For example, a cellular phone and a car communicate with each other using sidelink signals. The cellular phone and smart home devices communicate without relaying the communication signal through a base station.

[0063] The network device in the embodiments of the present application may be a device for communicating with a terminal device. The network device may also include an access network device. The access network device may also be referred to as a radio access network device or a base station. The access network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. Access network equipment can broadly cover various names as follows, or replace the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master eNB (MeNB), secondary eNB (SeNB), multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. A base station may also refer to a communication module, modem, or chip used to be set in the aforementioned device or apparatus. A base station may also be a mobile switching center and a device that performs base station functions in D2D, V2X, and machine-to-machine (M2M) communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. A base station may support networks with the same or different access technologies. The embodiments of this application do not limit the specific technology and specific device form used by the access network device.

[0064] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0065] In some deployments, the network device in the embodiments of the present application may refer to a CU or a DU, or the network device may include a CU and a DU. The gNB may also include an AAU.

[0066] The network equipment and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which the network equipment and terminal devices are located.

[0067] The communication equipment involved in the wireless communication system may include not only access network equipment and terminal equipment, but also core network equipment. The core network equipment may also be a type of network equipment.

[0068] The core network equipment in the embodiment of the present application may include equipment that processes and forwards user signaling and data. For example, the core network equipment may include a core network access and mobility management function (AMF), a session management function (SMF), and core network equipment such as a user plane gateway and a positioning server. Among them, the user plane gateway may be a server with functions such as mobility management, routing, and forwarding of user plane data, generally located on the network side, such as a serving gateway (SGW) or a packet data network gateway (PGW) or a user plane function entity (UPF). AMF and SMF can be equivalent to the mobility management entity (MME) in the LTE system. AMF is mainly responsible for access, and SMF is mainly responsible for session management. Of course, the core network may also include other network elements, which are not listed here one by one.

[0069] The positioning server has a positioning function. The positioning server involved in the embodiments of the present application may include a location management function (LMF) or a location management component (LMC), or may be a local location management function (LLMF) located in a network device, which is not limited in the embodiments of the present application. In some embodiments, the positioning server may also be referred to as a location management device.

[0070] It should be understood that all or part of the functions of the communication device in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (such as a cloud platform).

[0071] Positioning technology

[0072] With the continuous advancement of science and technology, various fields are experiencing rapid development. Simultaneously, the demand for location-based services continues to grow. Consequently, high-precision positioning methods have become a research hotspot. In wireless positioning systems, the location of mobile devices can be estimated by mapping signal characteristics to spatial locations. Positioning methods can be based on one or more of the following methods: ranging, angle, proximity, and fingerprinting.

[0073] For ranging-based positioning, a geometric body (such as a circle or hyperbola) can be constructed based on the distance from the terminal device to at least three network devices. Furthermore, the positioning result can be obtained by calculating the intersection between the geometric bodies. Time of arrival (TOA) and time difference of arrival (TDOA) are commonly used signal features in ranging-based positioning methods. Ranging positioning methods based on received signal strength (RSS) require fitting a path loss model.

[0074] For angle-based positioning, the position of the terminal device can be estimated by calculating the angle of arrival (AOA) of at least two input signals.

[0075] For proximity-based positioning, the range covered by the network device with the strongest RSS received by the terminal device can be used as the terminal device's location. The range covered by the network device is usually large, so this method is simple but has low positioning accuracy.

[0076] Fingerprint-based positioning methods, or fingerprint library positioning technology, are a commonly used indoor positioning method. This method can determine the indoor position based on the fingerprint characteristics of wireless signals. Fingerprint library positioning technology usually requires collecting positioning data of each reference point (such as wireless signal data and position data of the reference point) to form a fingerprint library. The accuracy of the positioning data (also called fingerprint data) of each reference point included in the fingerprint library depends to a large extent on the adequacy of the data set. In some embodiments, the fingerprint data can be input into a neural network for training to obtain a positioning model, which can be used for positioning the target positioning area.

[0077] The following is a detailed introduction to the fingerprint database construction process in combination with steps 1 to 4.

[0078] In step 1, the collection points are determined.

[0079] First, it is necessary to determine the locations of the collection points in the indoor area (i.e., the target positioning area). For example, the collection points can cover the entire target positioning area to ensure the integrity of the fingerprint data. In another example, the collection points should be representative, that is, they cover different environmental types in the target positioning area, such as different building structures and obstacle distribution in the target positioning area. In some cases, the collection points also need to take into account the usage of the device to be positioned.

[0080] Secondly, the number of collection points in the target positioning area can be determined based on the specific usage scenario. The amount of fingerprint data is closely related to the positioning accuracy of the fingerprint library positioning technology. Therefore, the number of collection points can be determined based on the positioning accuracy requirements. For example, when positioning accuracy is high, more collection points can be set; when positioning accuracy is low, fewer collection points can be set.

[0081] In step 2, fingerprint data is collected.

[0082] Data collection is performed at the collection points determined in step 1. For example, characteristics of wireless signals, such as the measurement results of the wireless signals and the location information of the collection points, can be recorded at a certain collection point. The measurement results of the wireless signals and the location information of the collection points constitute a set of fingerprint data.

[0083] In some embodiments, fingerprint data collection can be combined with the usage status of the target positioning device. For example, a user may use the target positioning device for positioning while walking or standing, meaning the target positioning device may be stationary or moving. Another example is that a user may use the target positioning device for positioning along a predetermined path, such as using the target positioning device on stairs. Based on this, data collection can be performed at specific collection points while simulating standing, walking, or walking along a predetermined path, recording wireless signal characteristics and corresponding location information.

[0084] In step 3, data is processed and stored.

[0085] To improve the reliability of fingerprint data, the fingerprint data can be preprocessed before storage. For example, the raw fingerprint data can be filtered and / or corrected to remove outliers or unstable data. The preprocessed fingerprint data can be stored in a data format supported by the fingerprint library, such as a database, file, or other data structure.

[0086] In step 4, data is updated and maintained.

[0087] In order to adapt to changes in the indoor environment, it is usually necessary to regularly update and maintain the fingerprint library data, such as adding new collection points, deleting invalid or outdated data, and updating the signal characteristics of existing data.

[0088] The environment type of the target positioning area mentioned above may include, for example, a line-of-sight type. The line-of-sight type can be divided into non-line-of-sight (NLOS) and line-of-sight (LOS). Line-of-sight may refer to the ability of the terminal device to be positioned and the first communication device to observe each other visually or with visual aids. Non-line-of-sight may refer to the inability of the terminal device to be positioned and the first communication device to observe each other visually or with visual aids. Figure 2 shows an example diagram of line-of-sight and non-line-of-sight. As shown in Figure 2, terminal device 121 is the terminal device to be positioned. Terminal device 121 is located in room 1. Network device 111 and network device 112 are both located in room 1. Since they are located in the same room and network device 111 or network device 112 and terminal device 121 can visually observe each other, the line-of-sight type between network device 111 and terminal device 121 can be line-of-sight, and the line-of-sight type between network device 112 and terminal device 121 can be line-of-sight. Network device 113 is located in room 2. Since Room 1 and Room 2 are separated by a wall, it is difficult for the network device 113 and the terminal device 121 to visually observe each other, and the line-of-sight type between the network device 113 and the terminal device 121 may be non-line-of-sight.

[0089] As can be seen from the fingerprint database construction process described above, indoor positioning technology requires considerable time and resources to establish a fingerprint database for the target location area. Fingerprint data collection is particularly cumbersome and time-consuming for large indoor areas or complex structures. In related technologies, fingerprint data is largely collected manually, resulting in a significant time and cost involved in collecting fingerprint data.

[0090] Furthermore, the accuracy of fingerprint-based positioning results is linked to the number of collection points. When there are fewer collection points, positioning accuracy is poor; as the number of collection points increases, positioning accuracy improves. This means that the accuracy of fingerprint-based positioning technology depends on the volume of data in the database. Therefore, to ensure accurate positioning results, it's not possible to reduce the time and resources required to collect fingerprint data simply by reducing the amount of data collected.

[0091] Furthermore, as mentioned earlier, the fingerprint database data needs to be regularly updated and maintained to adapt to changes in the indoor environment. Maintenance of the fingerprint database data, such as adding new collection points, deleting invalid or outdated data, and updating the signal characteristics of existing data, also requires continuous investment of resources and effort to ensure the accuracy and reliability of the fingerprint database.

[0092] One or more of the above reasons will involve a large amount of data processing work, which will increase the deployment time of fingerprint library positioning technology, thereby restricting the use and promotion of fingerprint library technology.

[0093] To address these issues, the applicant studied datasets from scenarios related to fingerprint database positioning technology. The applicant discovered that fingerprint data within a given area exhibits a certain degree of correlation, or that much collected fingerprint data is actually similar or redundant. Therefore, intensive data collection is unnecessary. The following describes the correlation of fingerprint data using a dataset from the 3GPP Indoor Factory High-Density Scenario (InF-DH) as an example.

[0094] Figure 3 is a schematic diagram of the fingerprint data location in a high-density indoor factory scene. The high-density indoor factory scene has dense clutter (60%) and a large number of base stations, and this scene is a highly NLOS scene.

[0095] As shown in Figure 3 , the densely populated indoor factory scenario includes 18 base stations 310, evenly distributed across a 120x60m indoor factory area 320 with a spacing of D. Figure 3 includes 80k data locations, where each point in indoor factory area 320 corresponds to a data location.

[0096] For ease of study, the area 320 can be divided into several grid cells according to a certain size, such as a side length of 2m*2m. Taking grid cell 330 as an example, each point in grid cell 330 corresponds to a fingerprint data, and the grid cell contains a total of 60 fingerprint data.

[0097] To observe the distribution differences between different amounts of data, several groups of fingerprint data can be generated based on the fingerprint data in grid unit 330. For example, a certain percentage of data can be selected from the 60 pieces of fingerprint data in grid unit 330 to form a new group of fingerprint data. Taking the formation of 10 groups of fingerprint data as an example, fingerprint data representing 10%, 20%, 30%, ..., and 100% of the total data volume can be selected from the fingerprint data in grid unit 330, respectively. In other words, each group of data represents a different proportion of the total data volume, and the data volume of each group gradually increases relative to the total data volume. Each group of data can be randomly selected from the fingerprint data in grid unit 330.

[0098] The Gaussian distribution curve for each data set is shown in Figure 4. Based on the Gaussian distribution of each data set, information about the data distribution, central tendency, and dispersion of that data set can be obtained. Referring to Figure 4, the Gaussian distribution of each data set corresponds to a curve in the figure, where the center of the curve corresponds to the mean of the data set, and the width and shape of the curve correspond to the standard deviation of the data set. The X-axis corresponds to the number of data sets, the Y-axis corresponds to the fingerprint data, and the Z-axis corresponds to the central tendency of the data distribution.

[0099] As can be seen from Figure 4, the curves for the third through tenth data sets show little difference. This means that the distribution characteristics of the third data set are similar to those of the fourth through tenth data sets. In other words, the distribution characteristics of the 30% data set are nearly identical to those of the 40%, 50%, ..., and 100% data sets.

[0100] In addition, the discreteness information for each set of data is shown in Figure 5 , where different color depths correspond to different discretenesses. The lower the data correlation, the greater the discreteness; the higher the data correlation, the weaker the discreteness. As can be seen in Figure 5 , the data in grid cell 330 is concentrated in the lower right corner of Figure 5 , and the discreteness is less than 0.1.

[0101] Therefore, the applicant has found that within a certain area, such as a grid unit, there is a strong correlation in the data distribution. Based on this, the embodiment of the present application provides a method for training a positioning model, by obtaining some extended fingerprint data (i.e., second data) based on the actual collected fingerprint data (i.e., first data), and using the first data and the second data to train the positioning model. In this way, in the process of establishing a fingerprint library, the amount of fingerprint data collected can be reduced, thereby helping to reduce the time and resource consumption of establishing the fingerprint library.

[0102] Figure 6 is a schematic flow chart of a method for training a positioning model provided in an embodiment of the present application. The method shown in Figure 6 may involve interaction between a network device and a terminal device. In some embodiments, the method shown in Figure 6 may also involve data exchange between a positioning server and a network device. The following describes in detail the method for training a positioning model provided in an embodiment of the present application from the perspective of interaction between a network device and a terminal device.

[0103] The method shown in Figure 6 includes step S610. In step S610, the terminal device sends first data to the network device, or in other words, the network device receives the first data sent by the terminal device.

[0104] The first data may be the fingerprint data for positioning mentioned above. For example, the first data may include a measurement result of a reference signal. As an example, the reference signal may be received signal strength (RSS), such as reference signal received power (RSRP). In another example, the first data may include location information, i.e., information for measuring the location of the first data, such as location coordinates.

[0105] In some embodiments, the reference signal may be sent by a network device to a terminal device. For example, the reference signal may be sent by one or more network devices to the terminal device. In other words, the fingerprint data, i.e., the first data, may be collected by the terminal device and one or more network devices. In this case, the terminal device may collect data from each network device separately and send the collected first data to the corresponding network device.

[0106] In some embodiments, the first data may be used to determine the second data. For example, the second data may be determined based on correlation between the data, such as the distribution characteristics of the first data. The distribution characteristics of the first data may include, for example, the dispersion, central tendency, and distribution location of the mean and standard deviation of the first data. As an example, the distribution characteristics of the first data may include that the first data follows a Gaussian distribution.

[0107] In some embodiments, the first data and the second data can be used as training data for a positioning model, which can be used to locate a terminal device in a target positioning area. For example, the positioning model can be used for indoor positioning based on a fingerprint library. The positioning model can be an artificial intelligence (AI) model. Alternatively, the positioning model can be a machine learning (ML) model.

[0108] By acquiring the second data based on the actually collected first data, the training data for the positioning model can be expanded, which helps to reduce the amount of fingerprint data collected, thereby helping to reduce the time and resource consumption caused by collecting a large amount of fingerprint data.

[0109] In some embodiments, the target positioning area may include a first grid unit, and the first data is a measurement result of the reference signal obtained when the terminal device is located in the first grid unit.

[0110] For example, the target positioning area can be divided into multiple grid cells, and the first grid cell can be any one of the multiple grid cells. In this case, the terminal device can send the first data corresponding to different grid cells to the network device. Before sending the first data, the terminal device can obtain the first data in each grid cell, that is, the terminal device measures the reference signal in each grid cell.

[0111] As mentioned above, the first data follows a Gaussian distribution. Based on this, in some embodiments, the expression for the joint Gaussian distribution of the first grid cells can be determined based on a mean matrix and a standard deviation matrix. This will be described later with reference to specific examples (such as step S3 mentioned later), and will not be repeated here.

[0112] It should be noted that the grid unit mentioned here refers to a sub-area of ​​the target positioning area, and the first grid unit can also be replaced by other names, such as the first sub-area, which is not limited in this application.

[0113] As mentioned above, the applicant discovered that fingerprint data within a certain area is correlated. Similarly, fingerprint data within the first grid unit is correlated. Based on this, the second data corresponding to the first grid unit can be determined based on the distribution characteristics of the first data within the first grid unit.

[0114] In some embodiments, the second data is obtained by random sampling within the distribution range of the first data. The distribution range of the first data can be determined based on the Gaussian distribution of the first data, for example. As an example, the distribution range of the first data can include data corresponding to distribution probability values ​​greater than zero. In other words, the second data can be randomly selected from the data with a distribution probability value greater than zero. In order to improve the validity of the second data, the second data can be randomly selected from the data with a distribution probability value greater than a first threshold. The first threshold can be determined based on usage requirements, such as the first threshold can be 0.1.

[0115] In some embodiments, the second data can be sampled and obtained within the distribution range of the first data based on the probability value, thereby helping to improve the reliability of the expanded data. The probability value mentioned here can be a data distribution probability value. That is, the second data can be sampled and obtained based on the data corresponding probability value within the distribution range of the first data. For example, the amount of second data collected can be proportional to the data corresponding probability value within the distribution range of the first data. That is, more data can be collected as the second data within the data range with a higher probability of occurrence (i.e., a higher probability value), and less data can be collected as the second data within the data range with a lower probability of occurrence (i.e., a lower probability value).

[0116] To further improve the reliability of the second data, the second data may be obtained based on the probability value from data having a distribution probability value greater than a second threshold value. The second threshold value may be the same as or different from the first threshold value.

[0117] In some embodiments, the distribution characteristic of the first data may be determined based on a Gaussian distribution curve, a probability density curve, or a probability distribution curve.

[0118] In the embodiments of the present application, obtaining the second data based on the aforementioned correlation between the data, such as the distribution characteristics of the first data, helps reduce the difference between the second data and the actual fingerprint data, that is, helps improve the accuracy of the second data. In this way, using both the first data and the second data as training data for the positioning model helps reduce the amount of fingerprint data collected while maintaining the positioning accuracy of the positioning model.

[0119] Before collecting fingerprint data in a target location area, it is necessary to first determine the distribution characteristics of the fingerprint data in the target location area, such as the distribution characteristics of the first data. In some embodiments, the distribution characteristics of the first data can be determined based on the distribution characteristics of data in the same or similar scenarios. For example, the distribution characteristics of the first data can be determined based on the distribution characteristics of third data. The third data can be a reference signal measurement result of a reference area, and the reference area is of the same type as the target location area.

[0120] In some embodiments, the reference area being of the same type as the target location area may refer to the reference area and the target location area having the same environment type. That is, the reference area of ​​the target location area may be determined based on the environment type. Examples of environment types include the ratio of direct path to indirect path, the ratio of line-of-sight to non-line-of-sight areas, the architectural structure and interior layout of the scene, and so on. For example, if the target location area is the first floor of a shopping mall, the reference area may be the second floor of the same mall, which has the same architectural structure as the first floor.

[0121] In some embodiments, the target positioning area includes a first grid area and a second grid area. If the environment type of the first grid area is the same as that of the second grid area, the distribution characteristics of the fingerprint data of the first grid area can be determined based on the distribution characteristics of the fingerprint data (i.e., the third data) of the second grid area.

[0122] In some embodiments, the amount of the first data can be determined based on the distribution characteristics of the third data. For example, if the distribution characteristics of 30% of the third data in the reference area are similar to those of 100% of the third data (as shown in FIG. 3 ), the amount of the first data can be 30% of the expected fingerprint data amount. The expected fingerprint data amount mentioned here can refer to the amount of training data determined based on the positioning accuracy of the positioning model.

[0123] If the positioning model training process involves multiple network devices, the amount of first data can be determined based on the distribution characteristics of the third data corresponding to the multiple network devices. The distribution characteristics of the third data corresponding to each network device may be different, that is, the initial amount of first data determined based on the third data corresponding to different network devices may be different.

[0124] In some embodiments, the amount of the first data can be determined based on the maximum value among the initial quantities of the first data. For example, if the distribution characteristics of 30% of the third data corresponding to the first network device are similar to the distribution characteristics of 100% of the data, then the first initial quantity of the first data can be 30% of the expected fingerprint data amount. If the distribution characteristics of 40% of the third data corresponding to the second network device are similar to the distribution characteristics of 100% of the data, then the second initial quantity of the first data can be 40% of the expected fingerprint data amount. Therefore, the amount of the first data can be the maximum value of the first and second initial quantities, i.e., 40% of the expected fingerprint data amount.

[0125] In some embodiments, the number of samples of the second data may be determined based on the number of the first data and the number of expected fingerprint data.

[0126] It should be noted that the second data includes extended data based on the reference signal measurement result, but the second data does not include corresponding location information.

[0127] In some embodiments, the second data used as data for positioning model training may be entirely or partially location-tagged. The location tag of the second data mentioned here may, for example, include location information corresponding to the second data. For the case where all the second data with location tags and the first data are used as training data, a positioning model can be obtained based on a neural network. For the case where partially the second data with location tags and the first data are used as training data, a semi-supervised learning method can be used to obtain a positioning model.

[0128] Since the area of ​​the grid unit region is small and the variation of the first data in the grid unit is also small, the position label corresponding to the second data is a position coordinate randomly generated in the first grid unit.

[0129] In some embodiments, the output of the positioning model may be the location coordinates and the location information of the first grid unit, or the location information of the first grid unit. The type of the output of the positioning model may be determined based on the positioning accuracy requirement. For scenarios where positioning accuracy is not required to be high, the output of the positioning model may be the location information of the grid unit. For scenarios where positioning accuracy is required to be high, the output of the positioning model may be the specific location coordinates and the location information of the first grid unit.

[0130] In some embodiments, the grid data (also referred to as a grid map) of the target positioning area can be updated based on the data of the user terminal. The grid data mentioned here may include, for example, grid location information and fingerprint library data corresponding to each grid. In the process of positioning using a positioning model, if the positioning result corresponding to the user terminal data, such as the measurement result of the reference signal, is a first grid unit, then the measurement result of the reference signal can be used to update the data of the first grid unit. For example, the measurement result of the reference signal can be used as the fingerprint library data corresponding to the first grid unit. Furthermore, the positioning model can be updated based on the update result of the grid map to improve the accuracy of the positioning model.

[0131] Since the grid map may occupy a large amount of storage resources, the grid map may be stored in a positioning server, for example.

[0132] The training process of the positioning model may involve multiple network devices, and this application does not limit the order of data collection. In some embodiments, the first data corresponding to multiple network devices in one grid unit can be collected separately, and then the first data corresponding to multiple network devices in another grid unit can be collected separately. In other embodiments, the first data of multiple grid units corresponding to one network device can be collected separately, and then the first data of multiple grid units corresponding to another network device can be collected separately.

[0133] The model training process usually consumes a lot of computing resources. Therefore, in order to avoid affecting the normal communication of network devices, the training of the positioning model can be performed by the positioning server.

[0134] The positioning server may receive first data and second data sent by the network device, or the network device may send the first data and second data to the positioning server. The second data is determined based on the first data, such as based on the distribution characteristics of the first data. Both the first data and the second data are training data for the positioning model.

[0135] The following describes the method for training a positioning model provided in an embodiment of the present application with reference to specific examples (steps S1 to S7).

[0136] In step S1, the target positioning area is divided into a number of grid units (including the first grid unit) with a side length of (x, y), and each grid unit represents a sub-area.

[0137] In step S2, fingerprint data collection (ie, collection of first data) is performed.

[0138] Before collecting fingerprint data, the terminal device can establish a connection with the network device.

[0139] Perform n fingerprint data collections in the first grid unit to obtain n pieces of fingerprint data.

[0140] If multiple network devices for positioning are deployed in the target positioning area, you can collect n pieces of fingerprint data for one network device and then switch to the next network device and repeat the above steps until all the fingerprint data corresponding to the network devices are collected to obtain the fingerprint data matrix of the first grid unit. Among them, data represents fingerprint data, n represents data number, and i represents base station number.

[0141] In step S3, the distribution characteristics of the first data are determined.

[0142] In the fingerprint data matrix, calculate the mean and standard deviation of the data under the same base station to obtain the mean matrix of the fingerprint data and standard deviation matrix

[0143] Furthermore, based on the mean matrix and standard deviation matrix, the expression of the joint Gaussian distribution of the grid cells is obtained:

[0144] in

[0145] The joint Gaussian distribution mentioned here may represent the Gaussian distribution of fingerprint data of the first grid units corresponding to all network devices.

[0146] In step S4, sampling is performed on each dimension of the joint Gaussian distribution obtained in step S3 to obtain m pieces of expanded fingerprint data, i.e., the second data. The size of the expanded fingerprint data (i.e., including the first data and the second data) is [i, m+n], where i represents the base station number, m+n represents the amount of fingerprint data under a single base station, and n represents n fingerprint data pieces obtained by performing n fingerprint data collections.

[0147] In some embodiments, random sampling may be performed on each dimension of the joint Gaussian distribution, or sampling may be performed based on the size of the probability, so as to obtain the second data.

[0148] In step S5, the above steps S1 to S4 are repeated for each grid unit to obtain the second data corresponding to all grid units.

[0149] In step S6, the second data is combined with the first data to obtain enhanced fingerprint data.

[0150] In step S7 , a location tag of the second data is generated.

[0151] Since the area of ​​each grid is very small and the difference in signal variation within the grid is also very small, a method of randomly generating coordinates within the grid can be used as the position label of the second data.

[0152] In some embodiments, the second data with the location tag and the first data can be input into a neural network for training to obtain a positioning model.

[0153] In other embodiments, part of the second data with labels, a large amount of the second data without labels, and the first data can be simultaneously fed into the artificial intelligence model, and a semi-supervised learning method can be used to obtain a positioning model.

[0154] In some embodiments, the network device may receive reference signal measurement results reported by the user and forward them to a positioning server. The positioning server may predict the user's location and / or the location information of the grid in which the user resides based on the aforementioned internally deployed positioning model. The positioning server may also send the user's location and / or the location information of the grid in which the user resides to the user via the network device.

[0155] In some embodiments, the positioning server includes grid distribution information of the target positioning area, such as the size and position information of the grids in the target positioning area.

[0156] The method provided by the embodiments of the present application can reduce the workload of collecting large amounts of fingerprint data in the target positioning area, thereby improving the efficiency of the positioning method. Furthermore, the method provided by the embodiments of the present application utilizes the principle of correlation between fingerprint data and performs random sampling based on the joint Gaussian distribution of the data to expand the amount of fingerprint data, thereby helping to reduce the time consumed by fingerprint collection.

[0157] In addition, the method provided in the embodiments of the present application can significantly reduce the workload of fingerprint collection while maintaining essentially unchanged positioning accuracy. For example, the method provided in the embodiments of the present application can reduce the amount of fingerprint collection to one-third of the original amount, thereby significantly reducing the consumption of time, manpower, and material resources. Because the method provided in the embodiments of the present application does not require the installation of additional hardware equipment or the upgrading and modification of existing hardware equipment, it is simple to implement and therefore has certain advantages and promotion prospects in high-precision indoor positioning application scenarios.

[0158] 7A to 7C , the following describes a method for training and using a positioning model provided by an embodiment of the present application.

[0159] Figure 7A is an example diagram of obtaining enhanced fingerprint data provided by an embodiment of the present application. Referring to Figure 7A, grid map 710 is the grid map corresponding to the actual sampled fingerprint data (i.e., the first data), and grid map 720 is the grid map corresponding to the enhanced fingerprint data (including the first data and the second data), where a is the number of the grid. Taking the x grid as an example, in the grid map 710, the points in the x grid represent the first data, and in the grid map 720, the points in the x grid represent the merged result of the first data and the second data. Among them, the second data is obtained based on the distribution characteristics of the first data, and the principle of obtaining the second data is shown in 730 in Figure 7A.

[0160] Figure 7B is an example diagram of a training positioning model provided by an embodiment of the present application. In Figure 7B , a machine learning-based model is used to train fingerprint data. The model's input is first data corresponding to multiple network devices (e.g., RSRP measurement results corresponding to access points 0 through 17), and its output is a positioning model. The positioning model can be trained based on a centralized unit.

[0161] The devices involved in the positioning process are related to the deployment location of the positioning model. In some embodiments, the positioning model can be deployed on a network device. In other embodiments, the positioning model can be deployed on a positioning server, thereby helping to conserve computing resources on the network device. The following describes the positioning process using the example of deploying the positioning model on a positioning server.

[0162] FIG7C is a flowchart of a method for using a positioning model provided by an embodiment of the present application. The method shown in FIG7C includes steps S710 to S750. The method shown in FIG7C involves interaction between a terminal device 701, a network device 702, and a positioning server 703.

[0163] In step S710, the network device may receive a measurement result of a reference signal sent by the terminal device, or in other words, the terminal device may send the measurement result of the reference signal to the network device. The reference signal may be sent by the network device.

[0164] In step S720, the network device may send the received measurement result to the positioning server, or in other words, the positioning server receives the measurement result sent by the network device.

[0165] In step S730, the positioning server generates a positioning result.

[0166] The positioning server can input the measurement results into the positioning model, and the positioning model can output the positioning results, which can be the location coordinates and / or the location information of the grid where the terminal device is located.

[0167] In step S740 , the positioning server sends the positioning result to the network device.

[0168] In step S750, the network device sends the positioning result to the terminal device.

[0169] In some embodiments, the method shown in Figure 7C may further include step S760 (not shown in the figure). In step S760, the positioning server may update the grid map, that is, the grid data of the target positioning area based on the positioning result. Further, the positioning server can update the positioning model based on the updated grid map.

[0170] By obtaining enhanced fingerprint data (i.e., first data and second data) based on the actually collected fingerprint data (i.e., first data), and training the positioning model based on the enhanced fingerprint data, it helps to reduce the amount of fingerprint data collected, thereby helping to reduce the time and resource consumption of establishing a fingerprint database, and reducing the deployment time of fingerprint database positioning technology.

[0171] The method embodiments of the present application are described in detail above, and the device embodiments of the present application are described in detail below. It should be understood that the description of the method embodiments corresponds to the description of the device embodiments. Therefore, the parts not described in detail can be referred to the previous method embodiments.

[0172] FIG8 is a schematic structural diagram of a terminal device provided in an embodiment of the present application. The device 800 includes: a sending unit 810.

[0173] The sending unit 810 may be used to send first data to the network device, where the first data is used to determine second data, and the first data and the second data are training data for a positioning model, and the positioning model is used to position the terminal device in a target positioning area; wherein the target positioning area includes a first grid unit, and the first data is a measurement result of a reference signal obtained when the terminal device is located in the first grid unit.

[0174] In some embodiments, the second data is obtained by random sampling within the distribution range of the first data, and / or the second data is obtained by sampling within the distribution range of the first data based on a probability value.

[0175] In some embodiments, the distribution characteristics of the first data are determined based on the distribution characteristics of third data, where the third data is a reference signal measurement result of a reference area, and the reference area is of the same type as the target positioning area.

[0176] In some embodiments, the amount of the first data is determined based on a data distribution characteristic of the third data.

[0177] In some embodiments, part or all of the second data is tagged with a location.

[0178] In some embodiments, the location tag corresponding to the second data is a randomly generated location coordinate within the first grid unit.

[0179] In some embodiments, the output result of the positioning model is the position coordinates and the position information of the first grid unit, or the position information of the first grid unit.

[0180] In some embodiments, the distribution characteristics of the first data include that the first data obeys a Gaussian distribution, and an expression of the joint Gaussian distribution of the first grid cells is determined based on a mean matrix and a standard deviation matrix.

[0181] FIG9 is a schematic structural diagram of a network device according to an embodiment of the present application. Device 900 may include a receiving unit 910 .

[0182] The receiving unit 910 is used to receive first data sent by a terminal device, where the first data is used to determine second data, and the first data and the second data are training data of a positioning model, and the positioning model is used to locate the terminal device in a target positioning area; wherein the target positioning area includes a first grid unit, and the first data is a measurement result of a reference signal obtained when the terminal device is located in the first grid unit.

[0183] In some embodiments, the second data is obtained by random sampling within the distribution range of the first data, and / or the second data is obtained by sampling within the distribution range of the first data based on a probability value.

[0184] In some embodiments, the distribution characteristics of the first data are determined based on the distribution characteristics of third data, where the third data is a reference signal measurement result of a reference area, and the reference area is of the same type as the target positioning area.

[0185] In some embodiments, the amount of the first data is determined based on a data distribution characteristic of the third data.

[0186] In some embodiments, part or all of the second data is tagged with a location.

[0187] In some embodiments, the location tag corresponding to the second data is a randomly generated location coordinate within the first grid unit.

[0188] In some embodiments, the output result of the positioning model is the position coordinates and / or the position information of the first grid unit, or the position information of the first grid unit.

[0189] In some embodiments, the distribution characteristics of the first data include that the first data obeys a Gaussian distribution, and an expression of the joint Gaussian distribution of the first grid cells is determined based on a mean matrix and a standard deviation matrix.

[0190] In an optional embodiment, the sending unit 810 and the receiving unit 910 may be a transceiver 1030. The device 800 or the device 900 may further include a processor 1010 and / or a memory 1020, as specifically shown in FIG10 .

[0191] Figure 10 is a schematic diagram of a device provided in an embodiment of the present application. Device 1000 can be a device for training a positioning model or a device for positioning. Dashed lines in Figure 10 indicate that the unit or module is optional. Device 1000 can be used to implement the method described in the above method embodiment. Device 1000 can be a nail device, a chip, a terminal device, or a network device.

[0192] The device 1000 may include one or more processors 1010. The processor 1010 may support the device 1000 to implement the method described in the method embodiment above. The processor 1010 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0193] The apparatus 1000 may further include one or more memories 1020. The memories 1020 store programs that can be executed by the processor 1010, causing the processor 1010 to perform the methods described in the above method embodiments. The memories 1020 may be independent of the processor 1010 or integrated into the processor 1010.

[0194] The apparatus 1000 may further include a transceiver 1030. The processor 1010 may communicate with other devices or chips via the transceiver 1030. For example, the processor 1010 may transmit and receive data with other devices or chips via the transceiver 1030.

[0195] The present application also provides a computer-readable storage medium for storing a program. The computer-readable storage medium can be applied to a terminal or network device provided in the present application, and the program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0196] The present application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to a terminal or network device provided in the present application, and the program causes a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0197] The embodiments of the present application also provide a computer program. The computer program can be applied to the terminal or network device provided in the embodiments of the present application, and the computer program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0198] It should be understood that the terms "system" and "network" in this application can be used interchangeably. In addition, the terms used in this application are only used to explain the specific embodiments of this application and are not intended to limit this application. The terms "first", "second", "third", and "fourth" in the specification and claims of this application and the accompanying drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0199] In the embodiments of this application, the term "indication" may refer to a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" may refer to a direct indication of B, e.g., B can obtain information through A; it may refer to an indirect indication of B, e.g., A indicates C, e.g., B can obtain information through C; or it may refer to an association between A and B.

[0200] In the embodiment of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0201] In the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and indication, configuration and configuration, etc.

[0202] In the embodiments of the present application, "pre-definition" or "pre-configuration" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., a terminal device and a network device). The present application does not limit the specific implementation method. For example, pre-definition may refer to information defined in a protocol.

[0203] In the embodiments of the present application, the “protocol” may refer to a standard protocol in the communications field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.

[0204] In the embodiments of this application, the term "and / or" is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0205] In the embodiments of this application, the term "include" can refer to direct inclusion or indirect inclusion. Alternatively, the term "include" in the embodiments of this application can be replaced with "indicates" or "is used to determine." For example, "A includes B" can be replaced with "A indicates B" or "A is used to determine B."

[0206] In various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0207] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0208] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0209] 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.

[0210] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part 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, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via 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 can be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0211] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for training a positioning model, characterized in that, Including: The terminal device sends first data to the network device. The first data is used to determine second data, and the first data and the second data are training data for a positioning model. The positioning model is used to position the terminal device within a target positioning area; Wherein, the target positioning area includes a first grid cell, and the first data is a measurement result of a reference signal obtained when the terminal device is located in the first grid cell.

2. The method according to claim 1, characterized in that, The second data is obtained by randomly sampling within the distribution range of the first data, and / or the second data is sampled within the distribution range of the first data based on a probability value.

3. The method according to claim 1 or 2, characterized in that, The distribution characteristic of the first data is determined based on the distribution characteristic of third data, where the third data is a measurement result of a reference signal in a reference area, and the reference area has the same type as the target positioning area.

4. The method according to claim 3, characterized in that, The quantity of the first data is determined based on the data distribution characteristic of the third data.

5. The method according to any one of claims 1 to 4, characterized in that, Some or all of the second data carries a position label.

6. The method according to claim 5, wherein The position label corresponding to the second data is a position coordinate randomly generated within the first grid cell.

7. The method according to any one of claims 1-6, characterized in that, The output result of the positioning model is a position coordinate and the position information of the first grid cell, or the position information of the first grid cell.

8. The method according to any one of claims 1-7, characterized in that, The distribution characteristic of the first data includes that the first data follows a Gaussian distribution, and the expression of the joint Gaussian distribution of the first grid cell is determined based on a mean matrix and a standard deviation matrix.

9. A method for training a positioning model, characterized in that, Including: The network device receives the first data sent by the terminal device. The first data is used to determine second data, and the first data and the second data are training data for a positioning model. The positioning model is used to position the terminal device within a target positioning area; Wherein, the target positioning area includes a first grid cell, and the first data is a measurement result of a reference signal obtained when the terminal device is located in the first grid cell.

10. The method according to claim 9, characterized in that The second data is obtained by randomly sampling within the distribution range of the first data, and / or the second data is sampled within the distribution range of the first data based on a probability value.

11. The method according to claim 9 or 10, characterized in that, The distribution characteristic of the first data is determined based on the distribution characteristic of third data, where the third data is a measurement result of a reference signal in a reference area, and the reference area has the same type as the target positioning area.

12. The method according to claim 11, wherein The quantity of the first data is determined based on the data distribution characteristic of the third data.

13. The method according to any one of claims 9-12, characterized in that, Some or all of the second data carries a position label.

14. The method according to claim 13, wherein The position label corresponding to the second data is a position coordinate randomly generated within the first grid cell.

15. The method according to any one of claims 9-14, characterized in that, The output result of the positioning model is a position coordinate and the position information of the first grid cell, or the position information of the first grid cell.

16. The method according to any one of claims 9-15, characterized in that, The distribution characteristic of the first data includes that the first data follows a Gaussian distribution, and the expression of the joint Gaussian distribution of the first grid cell is determined based on a mean matrix and a standard deviation matrix.

17. A terminal device, characterized in that, Including: A sending unit, configured to send first data to a network device, where the first data is used to determine second data, and the first data and the second data are training data of a positioning model, and the positioning model is used to position the terminal device in a target positioning area; Wherein, the target positioning area includes a first grid cell, and the first data is a measurement result of a reference signal obtained when the terminal device is located in the first grid cell.

18. The device according to claim 17, wherein The second data is obtained by randomly sampling within the distribution range of the first data, and / or the second data is sampled within the distribution range of the first data based on a probability value.

19. The device according to claim 17 or 18, characterized in that, The distribution characteristic of the first data is determined based on the distribution characteristic of third data, where the third data is a measurement result of a reference signal in a reference area, and the reference area is of the same type as the target positioning area.

20. The device according to claim 19, wherein The quantity of the first data is determined based on the data distribution characteristic of the third data.

21. The device according to any one of claims 17-20, characterized in that, Some or all of the second data are provided with position labels.

22. The device according to claim 21, characterized in that, The position label corresponding to the second data is a position coordinate randomly generated within the first grid cell.

23. The device according to any one of claims 17 - 22, characterized in that, The output result of the positioning model is a position coordinate and the position information of the first grid cell, or the position information of the first grid cell.

24. The device according to any one of claims 17-23, characterized in that, The distribution characteristic of the first data includes that the first data follows a Gaussian distribution, and the expression of the joint Gaussian distribution of the first grid cell is determined based on a mean matrix and a standard deviation matrix.

25. A network device, characterized in that, Comprising: A receiving unit, configured to receive first data sent by a terminal device, where the first data is used to determine second data, and the first data and the second data are training data of a positioning model, and the positioning model is used to position the terminal device in a target positioning area; Wherein, the target positioning area includes a first grid cell, and the first data is a measurement result of a reference signal obtained when the terminal device is located in the first grid cell.

26. The device according to claim 25, characterized in that, The second data is obtained by randomly sampling within the distribution range of the first data, and / or the second data is sampled within the distribution range of the first data based on a probability value.

27. The device according to claim 25 or 26, characterized in that, The distribution characteristic of the first data is determined based on the distribution characteristic of third data, where the third data is a measurement result of a reference signal in a reference area, and the reference area is of the same type as the target positioning area.

28. The device according to claim 27, wherein, The quantity of the first data is determined based on the data distribution characteristic of the third data.

29. The device according to any one of claims 25-28, characterized in that, Some or all of the second data are provided with position labels.

30. The device according to claim 29, characterized in that, The position label corresponding to the second data is a position coordinate randomly generated within the first grid cell.

31. The device according to any one of claims 25-30, characterized in that, The output result of the positioning model is a position coordinate and the position information of the first grid cell, or the position information of the first grid cell.

32. The device according to any one of claims 25 - 31, characterized in that, The distribution characteristic of the first data includes that the first data follows a Gaussian distribution, and the expression of the joint Gaussian distribution of the first grid cell is determined based on a mean matrix and a standard deviation matrix.

33. A terminal device, characterized in that, Comprising a memory and a processor, where the memory is used to store a program, and the processor is used to call the program in the memory to enable the terminal device to execute the method according to any one of claims 1-8.

34. A network device, characterized in that, It includes a memory and a processor. The memory is used for storing a program, and the processor is used for calling the program in the memory to enable the network device to execute the method according to any one of claims 9-16.

35. A device, characterized in that, It includes a processor for calling a program from a memory to enable the device to execute the method according to any one of claims 1-16.

36. A chip, characterized in that, It includes a processor for calling a program from a memory, such that the device installed with the chip executes the method according to any one of claims 1-16.

37. A computer-readable storage medium, characterized in that, A program is stored thereon, and the program enables a computer to execute the method according to any one of claims 1-16.

38. A computer program product, characterized in that, It includes a program, and the program enables a computer to execute the method according to any one of claims 1-16.

39. A computer program, characterized in that, The computer program enables a computer to execute the method according to any one of claims 1-16.

Images