Positioning method, network device, terminal device and communication system

Abstract

The invention provides a positioning method, network equipment, terminal equipment and a communication system, and relates to the technical field of communication, and the method comprises the steps: obtaining the environment information of an environment region where to-be-positioned terminal equipment is located; the CSI information and the environment information between the network equipment and the terminal equipment are input into a trained positioning model, the positioning information of the terminal equipment is obtained, and the positioning model is obtained by training the training sample data of the multiple environment areas in advance. According to the technical scheme, the positioning precision can be improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a positioning method, network equipment, terminal equipment and communication system. Background Art

[0002] Positioning technology can be applied to various fields such as navigation, surrounding search, emergency rescue, etc., providing many conveniences for people's daily life. Among them, the more commonly used positioning technology is based on satellite positioning systems, such as the global positioning system (GPS) and the Beidou navigation satellite system (BDS). However, the satellite positioning system has certain limitations. In indoor environments and urban environments, it is easily blocked by objects such as buildings, which may result in large positioning errors.

[0003] In order to make up for the shortcomings of the satellite positioning system, a positioning solution currently used is to use "location fingerprint" for positioning. Among them, "location fingerprint" is to correspond the terminal location in the actual environment with the fingerprint. The fingerprint can be a feature extracted from the wireless signal, and the more common one is the received signal strength (RSS). The fingerprint positioning technology specifically establishes the correspondence between the location and the fingerprint first, generates a fingerprint library; then, according to the measured RSS of the terminal device to be located, the fingerprint is matched in the fingerprint library, and the location of the terminal device is estimated to be the location corresponding to the best matching fingerprint.

[0004] However, in the above fingerprint positioning technology, RSS is easily affected by various environmental factors and has large fluctuations, thereby affecting the positioning accuracy. Summary of the invention

[0005] In view of this, the present application provides a positioning method, a network device, a terminal device and a communication system for improving positioning accuracy.

[0006] In order to achieve the above-mentioned purpose, in a first aspect, an embodiment of the present application provides a positioning method, which is applied to a network device, and the method includes:

[0007] Obtaining environmental information of the environment area where the terminal device to be located is located;

[0008] The CSI information between the network device and the terminal device and the environmental information are input into a trained positioning model to obtain the positioning information of the terminal device, wherein the positioning model is pre-trained using training sample data of multiple environmental areas.

[0009] The positioning method provided in the embodiment of the present application, when positioning a terminal device, inputs the CSI information between the network device and the terminal device and the environmental information of the environmental area where the terminal device is located into a trained positioning model to obtain the positioning information of the terminal device, wherein the positioning model is pre-trained using training sample data of multiple environmental areas, so that the positioning model can learn the correlation between the positioning information, CSI information and environmental information, and the predicted positioning information is related to the CSI information and the environmental information at the same time, thereby improving the accuracy of the prediction result, that is, improving the positioning accuracy; and the positioning model can be used to predict the positioning information of terminal devices in different environmental areas, thereby improving the versatility of the model and reducing the positioning cost.

[0010] In a possible implementation manner of the first aspect, when the positioning mode of the terminal device is the first positioning mode, the network device sends the positioning model and the environmental information to the terminal device after acquiring the environmental information, and the terminal device inputs the CSI information and the environmental information into the positioning model to obtain the positioning information of the terminal device;

[0011] When the positioning mode of the terminal device is the second positioning mode, the network device inputs the CSI information and the environmental information into the positioning model, obtains the positioning information of the terminal device, and then sends the positioning information to the terminal device.

[0012] In the above implementation manner, when positioning the terminal device, different positioning modes may be used for positioning, thereby improving the flexibility and adaptability of the positioning method.

[0013] In a possible implementation manner of the first aspect, the training sample data used by the network device to train the positioning model is determined based on uplink CSI information; before inputting the CSI information and the environmental information into the positioning model, the method further includes:

[0014] Receiving an uplink RS sent by the terminal device;

[0015] Determine the CSI information according to the uplink RS;

[0016] When the positioning mode of the terminal device is the first positioning mode, the CSI information is sent to the terminal device.

[0017] In the above implementation manner, the predicted positioning information is of the same type as the CSI information used in the training positioning model, which can improve the accuracy of the positioning result.

[0018] In a possible implementation manner of the first aspect, before inputting the CSI information and the environment information into the positioning model, the method further includes:

[0019] The initial prediction model is trained using first training sample data to obtain the positioning model, wherein the first training sample data includes training sample data of multiple environmental areas.

[0020] In a possible implementation of the first aspect, after training the initial prediction model to obtain the positioning model, the method further includes:

[0021] The positioning model is trained and updated using second training sample data, where the second training sample data includes training sample data of at least one environmental area.

[0022] Through the above implementation, the prediction performance of the model can be improved.

[0023] In a possible implementation of the first aspect, the method further includes:

[0024] Receiving a first RS and location information of the terminal device sent by the terminal device;

[0025] Determine first CSI information according to the first RS;

[0026] Generate training samples in the second training sample data according to the first CSI information and the location information of the terminal device.

[0027] In the above implementation, training samples can be generated online according to the location information of the terminal device, thereby improving the convenience of model training.

[0028] In a possible implementation of the first aspect, when the positioning mode of the terminal device is the third positioning mode, the network device sends the environmental information to the terminal device after acquiring the environmental information, and inputs the CSI information and the environmental information into the positioning model through the terminal device to obtain the positioning information of the terminal device, wherein the positioning model is trained by the terminal device.

[0029] In the above implementation, the model training and prediction processes are both performed on the terminal device side, thereby better meeting the user's privacy needs.

[0030] In a possible implementation of the first aspect, the training sample data used by the terminal device to train the positioning model is determined based on downlink CSI information; before the CSI information and the environmental information are input into the positioning model through the terminal device, the method further includes:

[0031] After receiving the positioning request sent by the terminal device, a downlink RS is sent to the terminal device, and the downlink RS is used by the terminal device to determine the CSI information.

[0032] In the above implementation manner, the predicted positioning information is of the same type as the CSI information used in the training positioning model, which can improve the accuracy of the positioning result.

[0033] In a possible implementation manner of the first aspect, before sending the environment information to the terminal device, the method further includes:

[0034] An initial prediction model and first training sample data are sent to the terminal device, where the first training sample data includes training samples of multiple environmental areas and is used by the terminal device to train the initial prediction model to obtain the positioning model.

[0035] In a possible implementation of the first aspect, after sending the initial prediction model to the terminal device, the method further includes:

[0036] A second RS is sent to the terminal device, where the second RS is used by the terminal device to generate training samples in second training sample data, so as to train and update the positioning model based on the second training sample data.

[0037] Through the above implementation, the terminal device can generate training samples online and train and update the positioning model, thereby improving the prediction performance of the model and enhancing the convenience of model training.

[0038] In a possible implementation of the first aspect, the method further includes:

[0039] receiving capability information sent by the terminal device, where the capability information is used to indicate computing capability and storage capability of the terminal device that can be used for positioning;

[0040] A positioning mode of the terminal device is determined according to the capability information.

[0041] In the above implementation manner, the positioning mode is determined according to the capability information of the terminal device, so that the positioning mode of the terminal device can be more reasonable.

[0042] In a possible implementation of the first aspect, the method further includes:

[0043] A message indicating the positioning mode is sent to the terminal device.

[0044] Through the above implementation, it is convenient for the terminal device to learn its own positioning mode.

[0045] In a possible implementation manner of the first aspect, the environmental information includes: spatial position information of each scatterer in an environmental area where the terminal device is located.

[0046] Scatterers in the environment are the main factors affecting signal transmission. In the above implementation, the environmental information includes the spatial position information of each scatterer in the environmental area where the terminal device is located. That is to say, the positioning model can learn the correlation between the positioning information, CSI information and the spatial position information of the scatterer. This can improve the positioning accuracy on the one hand, and reduce the amount of model input data on the other hand, thereby reducing the model complexity.

[0047] In a second aspect, an embodiment of the present application provides a positioning method, which is applied to a terminal device, and the method includes:

[0048] Receiving environmental information of an environmental area where the terminal device is located, sent by a network device;

[0049] The CSI information between the network device and the terminal device and the environmental information are input into a trained positioning model to obtain the positioning information of the terminal device, wherein the positioning model is pre-trained using training sample data of multiple environmental areas.

[0050] In a possible implementation of the second aspect, when the positioning mode of the terminal device is the first positioning mode, the terminal device receives the positioning model sent by the network device and the environmental information of the environmental area where the terminal device is located, inputs the CSI information and the environmental information into the positioning model, and obtains the positioning information of the terminal device;

[0051] When the positioning mode of the terminal device is the second positioning mode, the terminal device receives the positioning information of the terminal device sent by the network device, and the positioning information sent by the network device is obtained by the network device inputting the CSI information and the environmental information into the positioning model.

[0052] In a possible implementation manner of the second aspect, the positioning model is obtained by training the network device, and the training sample data used by the network device to train the positioning model is determined based on uplink CSI information; before inputting the CSI information and the environmental information into the positioning model, the method further includes:

[0053] Sending an uplink RS to the network device, where the uplink RS is used by the network device to determine the CSI information;

[0054] When the positioning mode of the terminal device is the first positioning mode, the CSI information sent by the network device is received.

[0055] In a possible implementation of the second aspect, the positioning model is obtained by the network device training an initial prediction model using first training sample data, and the method further includes:

[0056] A first RS and location information of the terminal device are sent to the network device, wherein the first RS is used by the network device to generate training samples in second training sample data, so as to train and update the positioning model based on the second training sample data.

[0057] In a possible implementation manner of the second aspect, when the positioning mode of the terminal device is the third positioning mode, before inputting the CSI information and the environment information into the positioning model, the method further includes:

[0058] Receiving an initial prediction model and first training sample data sent by the network device, where the first training sample data includes training sample data of multiple environmental areas;

[0059] The first training sample data is used to train the initial prediction model to obtain a positioning model.

[0060] In a possible implementation manner of the second aspect, the training sample data used by the terminal device to train the positioning model is determined based on downlink CSI information; before inputting the CSI information and the environmental information into the positioning model, the method further includes:

[0061] Sending a positioning request to the network device;

[0062] Receiving a downlink RS sent by the network device;

[0063] The CSI information is determined according to the downlink RS.

[0064] In a possible implementation of the second aspect, after training the initial prediction model to obtain the positioning model, the method further includes:

[0065] The positioning model is trained and updated using second training sample data, where the second training sample data includes training sample data of at least one environmental area.

[0066] In a possible implementation manner of the second aspect, the method further includes:

[0067] Receiving a second RS sent by the network device;

[0068] Determine second CSI information according to the second RS;

[0069] Generate training samples in second training sample data according to the second CSI information and the location information of the terminal device.

[0070] In a possible implementation manner of the second aspect, the method further includes:

[0071] Sending capability information to the network device, where the capability information is used to indicate computing capability and storage capability of the terminal device that can be used for positioning;

[0072] A message sent by the network device to indicate a positioning mode of the terminal device is received, where the positioning mode is determined by the network device based on the capability information.

[0073] In a possible implementation manner of the second aspect, the environmental information includes: spatial position information of each scatterer in the environmental area where the terminal device is located.

[0074] In a third aspect, an embodiment of the present application provides a communication device, applied to a network device, the device comprising:

[0075] A processing module, used to obtain environmental information of an environmental area where a terminal device to be located is located;

[0076] The processing module is also used to input the CSI information and the environmental information between the network device and the terminal device into a trained positioning model to obtain the positioning information of the terminal device, wherein the positioning model is pre-trained using training sample data from multiple environmental areas.

[0077] In a possible implementation manner of the third aspect, the device further includes: a transceiver module;

[0078] The processing module is specifically used to: when the positioning mode of the terminal device is the first positioning mode, after acquiring the environmental information, instruct the transceiver module to send the positioning model and the environmental information to the terminal device, so that the CSI information and the environmental information are input into the positioning model through the terminal device to obtain the positioning information of the terminal device;

[0079] The transceiver module is also used for: when the positioning mode of the terminal device is the second positioning mode, the processing module inputs the CSI information and the environmental information into the positioning model, and after obtaining the positioning information of the terminal device, sends the positioning information to the terminal device.

[0080] In a possible implementation manner of the third aspect, the training sample data used by the network device to train the positioning model is determined based on uplink CSI information;

[0081] The transceiver module is also used to: receive an uplink RS sent by the terminal device;

[0082] The processing module is further used to: determine the CSI information according to the uplink RS;

[0083] The transceiver module is also used to: when the positioning mode of the terminal device is the first positioning mode, send the CSI information to the terminal device.

[0084] In a possible implementation manner of the third aspect, the processing module is further used to:

[0085] Before inputting the CSI information and the environmental information into the positioning model, first training sample data is used to train an initial prediction model to obtain the positioning model, and the first training sample data includes training sample data of multiple environmental areas.

[0086] In a possible implementation manner of the third aspect, the processing module is further used to:

[0087] After the initial prediction model is trained to obtain the positioning model, the positioning model is trained and updated using second training sample data, where the second training sample data includes training sample data of at least one environmental area.

[0088] In a possible implementation manner of the third aspect, the transceiver module is further used to: receive a first RS sent by the terminal device and location information of the terminal device;

[0089] The processing module is further used to: after determining the first CSI information according to the first RS; generate the training samples in the second training sample data according to the first CSI information and the location information of the terminal device.

[0090] In a possible implementation manner of the third aspect, the device further includes: a transceiver module;

[0091] The processing module is specifically used for: when the positioning mode of the terminal device is the third positioning mode, after acquiring the environmental information, instructing the transceiver module to send the environmental information to the terminal device, so as to input the CSI information and the environmental information into the positioning model through the terminal device to obtain the positioning information of the terminal device, wherein the positioning model is obtained by training the terminal device.

[0092] In a possible implementation of the third aspect, the training sample data used by the terminal device to train the positioning model is determined based on downlink CSI information; and the transceiver module is further used to:

[0093] Before the processing module inputs the CSI information and the environmental information into the positioning model through the terminal device, after receiving the positioning request sent by the terminal device, a downlink RS is sent to the terminal device, and the downlink RS is used by the terminal device to determine the CSI information.

[0094] In a possible implementation of the third aspect, the transceiver module is also used to: before sending the environmental information to the terminal device, send an initial prediction model and first training sample data to the terminal device, the first training sample data including training samples of multiple environmental areas, which are used for the terminal device to train the initial prediction model to obtain the positioning model.

[0095] In a possible implementation of the third aspect, the transceiver module is also used to: after sending the initial prediction model to the terminal device, send a second RS to the terminal device, and the second RS is used for the terminal device to generate training samples in second training sample data, so as to train and update the positioning model based on the second training sample data.

[0096] In a possible implementation manner of the third aspect, the transceiver module is further used to: receive capability information sent by the terminal device, where the capability information is used to indicate a computing capability and a storage capability of the terminal device that can be used for positioning;

[0097] The processing module is further used to determine the positioning mode of the terminal device according to the capability information.

[0098] In a possible implementation manner of the third aspect, the transceiver module is further used to: send a message indicating the positioning mode to the terminal device.

[0099] In a possible implementation manner of the third aspect, the environmental information includes: spatial position information of each scatterer in the environmental area where the terminal device is located.

[0100] In a fourth aspect, an embodiment of the present application provides a communication device, applied to a terminal device, the device comprising:

[0101] A transceiver module, used for receiving environmental information of the environment area where the terminal device is located, sent by a network device;

[0102] A processing module is used to input the CSI information and the environmental information between the network device and the terminal device into a trained positioning model to obtain the positioning information of the terminal device, wherein the positioning model is pre-trained using training sample data of multiple environmental areas.

[0103] In a possible implementation of the fourth aspect, the transceiver module is specifically used to: when the positioning mode of the terminal device is the first positioning mode, receive the positioning model sent by the network device and the environmental information of the environmental area where the terminal device is located; the processing module is specifically used to: input the CSI information and the environmental information into the positioning model received by the transceiver module to obtain the positioning information of the terminal device;

[0104] The transceiver module is also used to: when the positioning mode of the terminal device is the second positioning mode, receive the positioning information of the terminal device sent by the network device, and the positioning information sent by the network device is obtained by the network device inputting the CSI information and the environmental information into the positioning model.

[0105] In a possible implementation of the fourth aspect, the positioning model is obtained by training the network device, and the training sample data used by the network device to train the positioning model is determined based on uplink CSI information; the transceiver module is further used to:

[0106] Sending an uplink RS to the network device, where the uplink RS is used by the network device to determine the CSI information;

[0107] When the positioning mode of the terminal device is the first positioning mode, the CSI information sent by the network device is received.

[0108] In a possible implementation of the fourth aspect, the positioning model is obtained by the network device using the first training sample data to train an initial prediction model, and the transceiver module is further used to:

[0109] A first RS and location information of the terminal device are sent to the network device, wherein the first RS is used by the network device to generate training samples in second training sample data, so as to train and update the positioning model based on the second training sample data.

[0110] In a possible implementation of the fourth aspect, the transceiver module is further used to: when the positioning mode of the terminal device is the third positioning mode, before the processing module inputs the CSI information and the environmental information into the positioning model, receive the initial prediction model and first training sample data sent by the network device, wherein the first training sample data includes training sample data of multiple environmental areas;

[0111] The processing module is also used to: use the first training sample data to train the initial prediction model to obtain a positioning model.

[0112] In a possible implementation of the fourth aspect, the training sample data used by the terminal device to train the positioning model is determined based on the downlink CSI information; the transceiver module is further used to: send a positioning request to the network device before the processing module inputs the CSI information and the environmental information into the positioning model; receive the downlink RS sent by the network device;

[0113] The processing module is further used to: determine the CSI information according to the downlink RS.

[0114] In a possible implementation of the fourth aspect, the processing module is also used to: after training the initial prediction model to obtain the positioning model, use second training sample data to train and update the positioning model, and the second training sample data includes training sample data of at least one environmental area.

[0115] In a possible implementation manner of the fourth aspect, the transceiver module is further used to: receive a second RS sent by the network device;

[0116] The processing module is further used to: after determining the second CSI information according to the second RS; generate a training sample in the second training sample data according to the second CSI information and the location information of the terminal device.

[0117] In a possible implementation manner of the fourth aspect, the transceiver module is further used to:

[0118] Sending capability information to the network device, where the capability information is used to indicate computing capability and storage capability of the terminal device that can be used for positioning;

[0119] A message sent by the network device to indicate a positioning mode of the terminal device is received, where the positioning mode is determined by the network device based on the capability information.

[0120] In a possible implementation manner of the fourth aspect, the environmental information includes: spatial position information of each scatterer in the environmental area where the terminal device is located.

[0121] In a fifth aspect, an embodiment of the present application provides a network device, comprising: a memory and a processor, the memory being used to store a computer program; the processor being used to execute the method described in the first aspect or any one of the implementations of the first aspect when calling the computer program.

[0122] In a sixth aspect, an embodiment of the present application provides a terminal device, comprising: a memory and a processor, the memory being used to store a computer program; the processor being used to execute the method described in the second aspect or any one of the implementations of the second aspect when calling the computer program.

[0123] In a seventh aspect, an embodiment of the present application provides a communication system, comprising: the network device described in the fifth aspect above and the terminal device described in the sixth aspect above.

[0124] In an eighth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method described in the first aspect or the second aspect above is implemented.

[0125] In a ninth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a communication device, the communication device executes the method described in the first aspect or any one of the implementation methods of the first aspect.

[0126] In a tenth aspect, an embodiment of the present application provides a chip system, including a processor, the processor is coupled to a memory, and the processor executes a computer program stored in the memory to implement the method described in the first aspect or the second aspect above. The chip system can be a single chip or a chip module composed of multiple chips.

[0127] It can be understood that the beneficial effects of the second to tenth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0128] Figure 1 A schematic diagram of a fingerprint positioning scenario provided in an embodiment of the present application;

[0129] Figure 2 A schematic diagram of a positioning method based on deep learning provided in an embodiment of the present application;

[0130] Figure 3 A schematic diagram of the system architecture of a communication system provided in an embodiment of the present application;

[0131] Figure 4 A schematic diagram of a flow chart of a positioning method provided in an embodiment of the present application;

[0132] Figure 5 A schematic diagram of the environmental reconstruction result provided in an embodiment of the present application;

[0133] Figure 6 A schematic diagram of the positioning principle of the positioning model provided in the embodiment of the present application;

[0134] Figure 7 A schematic diagram of the positioning process corresponding to positioning mode 1 provided in an embodiment of the present application;

[0135] Figure 8 A schematic diagram of the positioning process corresponding to positioning mode 2 provided in an embodiment of the present application;

[0136] Fig. 9A schematic diagram of the positioning process corresponding to positioning mode 3 provided in an embodiment of the present application;

[0137] Fig.10 A schematic diagram of the structure of a communication device provided in an embodiment of the present application;

[0138] Fig.11 A schematic diagram of the structure of a communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0139] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the embodiments of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0140] At present, positioning technology has been widely used in various fields. Among them, the more commonly used satellite positioning technology is prone to large positioning deviations when blocked by objects such as buildings. Therefore, it has certain limitations in environments with many obstructions such as indoor environments and cities. Positioning technologies based on other wireless communication networks can make up for the shortcomings of satellite positioning technology to a certain extent and improve positioning accuracy.

[0141] A related positioning technology is to use "location fingerprint" for positioning, where a location corresponds to a unique fingerprint, which can be single-dimensional or multi-dimensional. For example, when the terminal device to be positioned sends or receives a wireless signal, the fingerprint can be one or more features extracted from the signal, among which RSS is commonly used. Positioning using location fingerprints usually includes two stages: offline stage and online stage.

[0142] In the offline stage, fingerprints at various locations are collected, the corresponding relationship between the location and the fingerprint is established, and a fingerprint library is constructed. Specifically, Figure 1As shown, the geographical area is covered by a rectangular grid, which is divided into multiple rows and columns (here exemplarily 4 rows and 10 columns) of grids (a total of 40 grid points). It can be understood that the figure only uses black squares to indicate the location of the grid, not to indicate the coverage area of ​​the grid; exemplarily, the area contains two base stations BS1 and BS2, where the BS can be used for both communication and positioning. At each grid point, the average RSS from each BS is obtained by sampling data for a period of time (for example, the sampling time is 5 to 10 minutes and the sampling interval is 1s); the fingerprint at a grid point is a two-dimensional vector S = [s1, s2] containing RSS, where s1 represents the average RSS from the first base station BS1, and s2 represents the average RSS from the second base station BS2. Of course, the distribution of RSS or other features of the received signal can also be used as fingerprints. These two-dimensional fingerprints are collected in the area shown by each grid point, and these grid point coordinates and corresponding fingerprints form a database, namely a fingerprint library.

[0143] In the online stage, for the terminal device to be located in this geographical area, if the terminal device measures the RSS from each BS, r = [r1, r2]; when determining the location of the terminal device, fingerprint matching can be performed in the fingerprint library collected in the offline stage to find the fingerprint that best matches r. The location of the terminal device can be estimated as the location corresponding to the best matching fingerprint.

[0144] In the above-mentioned fingerprint positioning technology, RSS is easily affected by environmental factors such as multipath effect and path attenuation and has large fluctuations, thus affecting the positioning accuracy; moreover, in the offline stage, tedious collection is required in the designated area, which is costly.

[0145] Another related positioning technology is the positioning solution based on deep learning, such as Figure 2 As shown in the figure, the scheme uses neural network and channel state information (CSI) for location prediction, which can be divided into two parts: offline training and online prediction. In the offline training stage, the paired CSI information and location can be used as input and sent to the neural network for training to obtain a prediction model. In the online prediction stage, the location of the terminal device can be predicted by the received CSI.

[0146] Among them, when the signal is sent from the transmitter, it will be affected by the physical space environment during the transmission process, forming multiple paths such as direct, reflected and scattered to produce multipath effects. At the same time, electromagnetic waves will also produce attenuation and loss during space propagation. The signal received by the receiver reflects the multipath superposition characteristics of environmental characteristic information.

[0147] CSI is a channel property that describes a wireless communication link. It describes the transmission environment information of the signal between the transmitter and the receiver, such as signal scattering, environmental attenuation, and distance attenuation. The frequency domain model of the channel state can be described as:

[0148] Y = HX + N (1)

[0149] Among them, Y represents the received signal, X represents the transmitted signal, H represents the channel matrix, and H represents Gaussian white noise. The channel matrix H describes the attenuation factor of the signal on each transmission path, and each element contains information such as signal scattering, environmental attenuation, and distance attenuation.

[0150] The CSI information can be represented by the channel matrix H. After receiving the signal, the receiving end can determine the CSI information based on the above formula (1).

[0151] Compared with RSS, CSI takes into account multiple propagation factors such as signal scattering, environmental attenuation and distance attenuation, provides more detailed information, and has better stability and location sensitivity. Therefore, the positioning scheme based on CSI information can obtain more accurate positioning results; in addition, the positioning scheme can learn better features through deep learning methods to improve positioning accuracy, and only a certain amount of samples are needed to learn better features. Compared with the fingerprint positioning scheme based on RSS, it can effectively reduce costs.

[0152] However, the above two positioning solutions are both for positioning in a certain environment. Once the environment changes or migrates to other environments, the positioning performance will drop sharply. Therefore, it is necessary to establish a corresponding fingerprint library or prediction model for each environment, which has poor versatility and high cost.

[0153] To this end, an embodiment of the present application provides a positioning solution, which introduces environmental information to establish a positioning model based on environmental priors. When performing positioning, the location of the terminal device to be located is predicted through the positioning model based on the environmental information and CSI information of the terminal device to be located, so as to improve the positioning accuracy while improving the model versatility and reducing the positioning cost.

[0154] In the embodiments of the present application, the estimated / predicted position is referred to as positioning, which can be understood as determining the coordinates in the physical space (i.e., the coordinates of the terminal device). The coordinates can be absolute coordinates in an absolute coordinate system (e.g., a Cartesian coordinate system, a polar coordinate system, a geographic coordinate system), or can be relative coordinates relative to a reference point. In the embodiments of the present application, Cartesian coordinates are used as an example for illustrative explanation.

[0155] The positioning scheme of the embodiment of the present application can be applied to various communication systems, for example, Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD), Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication system, 4G, 5G mobile communication system (including independent networking and non-independent networking), New Radio (NR), or future-oriented evolution system (such as 6G mobile communication system), cloud radio access network (CRAN), etc., or it can also be a communication system in which two or more of the above systems are integrated. The above-mentioned communication system applicable to the present application is only an example, and the communication system applicable to the present application is not limited thereto.

[0156] To facilitate understanding of the embodiments of the present application, Figure 3 The communication system shown in the figure is used as an example to describe in detail the communication system applicable to the embodiments of the present application. Figure 3 A schematic diagram of a communication system is shown. Figure 3 As shown, the communication system may include: a network device 100 and a terminal device 200.

[0157] Among them, the network device 100 is a device with wireless transceiver functions or a chip that can be set in the device. The device can be: a base station (BS), an evolved node B (eNB), a home base station, an access point (AP) in a wireless fidelity (Wi-Fi) system, a wireless relay node, a wireless backhaul node, a transmission point (TP) or a transmission and reception point (TRP), etc.; it can also be a gNB in ​​an NR system, or a wireless controller in a CRAN system; it can also be a component or a part of the equipment that constitutes a base station, such as a central unit (CU), a distributed unit (DU) or a baseband unit (BBU), etc.

[0158] The terminal device 200 may also be referred to as a terminal, user equipment (UE), a mobile station, a mobile terminal, etc. The terminal may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a wearable device, a vehicle, a drone, a helicopter, an airplane, a ship, a robot, a mechanical arm, a smart home device, etc. The embodiment of the present application does not specifically limit the specific technology and specific device form adopted by the terminal device 200.

[0159] It should be understood that Figure 3 The simplified schematic diagram is only provided for the sake of ease of understanding. The communication system may further include other network devices 100 or other terminal devices 200 . The number of network devices 100 and terminal devices 200 is not limited.

[0160] In the communication system, a node can send a signal to at least one other node; or can receive a signal sent by at least one other node. The node here can refer to the network device 100 or the terminal device 200, etc. For example, Figure 3 The terminal device 200 can send signals to the network device 100, and can also receive signals sent by the network device 100.

[0161] In the embodiment of the present application, the network device 100 or the terminal device 200 can predict the positioning information of the terminal device 200 through the trained positioning model according to the CSI information between the network device 100 and the terminal device 200 and the environmental information of the environmental area where the terminal device 200 is located. The positioning process is described in detail below.

[0162] Figure 4 A flow chart of the positioning method provided in the embodiment of the present application is shown as follows: Figure 4 As shown, the positioning process provided in the embodiment of the present application may include the following steps:

[0163] S100: Obtain environmental information of an environmental area where a terminal device to be located is located.

[0164] In the environment where the terminal device is located, scatterers that affect the transmission of signals between the network device and the terminal device include but are not limited to: buildings, plants, furniture, electrical appliances, etc. In the embodiment of the present application, environmental information can be obtained by scanning through the network device, and the environmental information can reflect the scatterer information in the environment.

[0165] Specifically, the environmental information can be point cloud data obtained by scanning by network equipment. The network equipment can generate a series of point cloud data by emitting electromagnetic waves based on echo information (such as echo delay) and beam pointing information. The echo information is related to the position of the scatterer, and the point cloud data generated based on the echo information can reflect the spatial position information of the scatterer in the environment. The network equipment can also use other technologies, such as beamforming, lidar, millimeter waves, multi-sensors, etc., to sense the environment within the coverage area and generate point cloud data.

[0166] Considering that the amount of point cloud data is relatively large, in some embodiments, semantic extraction may be performed on the point cloud data to obtain target scattering point data of the scatterer to compress the data amount.

[0167] Specifically, the point cloud data can be denoised and clustered, and then the clustered scatterers can be characterized through operations such as the minimum bounding box, thereby determining the target scattering point data of each scatterer to achieve reconstruction of the environment.

[0168] Among them, the scatterer can be a three-dimensional structure or a planar structure, and the scatterer can be represented by the vertex data of the scatterer, and each scatterer can be represented by multiple vertices; the scattering point data of each vertex can include the position coordinates of the vertex, and the position coordinates can be the absolute coordinates in the aforementioned absolute coordinate system, or the relative coordinates relative to the reference point. In the embodiment of the present application, Cartesian coordinates (x, y, z) are used as an example for illustrative explanation. The scattering point data of the scatterer can also include other information, such as type, speed, etc., which is not particularly limited in the embodiment of the present application.

[0169] For example, Figure 5 As shown, the reconstructed indoor environment includes 7 scatterers. Correspondingly, the environmental information of the indoor environment may include vertex data of each scatterer, where (x i,j ,y i,j , z i,j ) represents the position coordinates of the jth vertex of the i-th scatterer. It can be understood that, Figure 5 The planar scatterer is used as an example for illustrative description. In actual applications, the scatterer may be three-dimensional or in other shapes, and may be represented by other numbers of vertices.

[0170] In some scenarios, the amount of scattering point data may still be too large. In this case, the scattering point data can be further compressed to achieve extraction of higher-level semantics. For example, polygon fitting data of the scatterer can be extracted, and the polygon fitting data can include: center point coordinates, size, normal direction, etc.; or, the scatterer can be mapped to a two-dimensional plane and represented by two-dimensional scattering point data.

[0171] The environment information constructed by the network device may include the above-mentioned scatterer information, and may also include other information, such as the time when the environment information is constructed.

[0172] It can be understood that the above only shows several ways of representing environmental information, and the representation of environmental information is not limited to this. The specific form can be selected according to actual needs, and the embodiments of the present application do not specifically limit this.

[0173] In addition, when reconstructing the environment, the network device can build it based on the data scanned by itself or in combination with the data scanned by other network devices; and can scan the environment regularly and update the environmental information. The network device can establish the corresponding environmental information for the covered area as one environmental area; it can also divide the covered area into multiple environmental areas and establish the environmental information for each environmental area, so that when performing subsequent position prediction, it can reduce input information, improve positioning speed, and reduce communication load.

[0174] It is understandable that after the network device obtains the environmental information of a certain environmental area through environmental reconstruction / environmental update, it can store the environmental information, and when it needs to locate and obtain the environmental information again later, it only needs to read the required environmental information.

[0175] S200. Input the CSI information between the network device and the terminal device and the above-mentioned environmental information into the trained positioning model to obtain the positioning information of the terminal device.

[0176] like Figure 6 As shown, in an embodiment of the present application, the positioning model is used to predict the positioning information based on the CSI information and the environmental information, that is, the positioning model learns the correlation between the positioning information, the CSI information and the environmental information, and the predicted positioning information is related to the CSI information and the environmental information at the same time, so that the prediction result is more reliable, that is, the positioning accuracy is higher; at the same time, the positioning model can also be used to predict the positioning information of terminal devices in different environmental areas, thereby improving the versatility of the model and reducing the positioning cost.

[0177] The positioning model may be pre-trained using training sample data of multiple environmental areas. The training sample data of each environmental area may include multiple training samples.

[0178] Specifically, for each environmental area, CSI information corresponding to multiple locations can be collected in advance; for each location, the CSI information collected at the location and the environmental information of the location are used as input data of the training sample, and the coordinates of the location (i.e., location information, or sample positioning information) are used as label data of the training sample to generate the corresponding training sample.

[0179] Among them, the CSI information can be CSI information (i.e., uplink CSI information) determined based on the uplink signal (i.e., the signal sent by the terminal device to the network device), or it can be CSI information (i.e., downlink CSI information) determined based on the downlink signal (i.e., the signal sent by the network device to the terminal device).

[0180] Specifically, the CSI information may be determined according to a reference signal (RS) in the uplink signal / downlink signal through the above formula (1); wherein the RS may be any reference signal that can be used to measure the CSI information, for example, the RS is a positioning reference signal (PRS).

[0181] The location information may be represented by absolute coordinates or relative coordinates, which is not particularly limited in the embodiments of the present application.

[0182] The training samples can be collected manually or generated online based on the location information reported by the terminal device. In some embodiments, the training sample data can be generated by combining manual collection with online generation, so as to obtain abundant training samples while reducing costs.

[0183] In an embodiment of the present application, training samples may be collected for coverage areas of multiple network devices to obtain training sample data for multiple environmental areas, thereby increasing the diversity of training samples.

[0184] After obtaining the training sample data, the training sample data can be used to train the initial prediction model to obtain the positioning model.

[0185] Among them, the initial prediction model can adopt a neural network model such as a convolutional neural network or a graph neural network, or other machine learning models such as a decision tree.

[0186] During training, the training sample data can be divided into a training set and a test set, or divided into a training set, a test set and a validation set to complete the training of the initial prediction model. The specific training process can refer to the relevant training technology, which will not be repeated here.

[0187] In order to improve the prediction performance of the model, after the initial prediction model is trained using the above-mentioned training sample data (hereinafter referred to as the first training sample data) to obtain the positioning model, the newly acquired training sample data (hereinafter referred to as the second training sample data) can also be used to train and update the positioning model.

[0188] Among them, similar to the first training sample data, the training samples of the second training sample data can be generated by manual collection and / or online generation; in some embodiments, they can be generated online according to the location information of the terminal device to improve the convenience of model training.

[0189] After obtaining the trained positioning model, when you need to locate the terminal device, you can Figure 6 As shown, the CSI information between the network device and the terminal device and the environmental information of the environment area where the terminal device is located are input into the positioning model for prediction to obtain the positioning information of the terminal device.

[0190] Similar to the training samples, the CSI information may be uplink CSI information or downlink CSI information; in some embodiments, the predicted positioning information is of the same type as the CSI information used in the training positioning model to improve the accuracy of the positioning result.

[0191] The above-mentioned process of training the initial prediction model to obtain the positioning model (referred to as the model training process) and the process of predicting the positioning information through the positioning model (referred to as the model prediction process) can both be executed on the network device; they can also both be executed on the terminal device. At this time, the terminal device can obtain environmental information and training sample data from the network device; the model training process and the model prediction process can also be partially executed on the network device and partially executed on the terminal device.

[0192] Considering that the model training process and the model prediction process require certain computing power and storage capacity, in some embodiments, multiple positioning modes can be defined based on the capability information of the terminal device (including computing power and storage capacity) to adapt to different application scenarios.

[0193] Among them, model training requires higher computing power and storage capacity (for storing training sample data); model prediction requires a certain amount of computing power and storage capacity (for storing environmental information of the environment area where the terminal device is located), but compared with model training, the required computing power and storage capacity are relatively low. When the terminal device has the computing power and storage capacity required for model training, it also has the computing power and storage capacity required for model prediction. Based on this, three positioning modes can be defined as shown in the following table:

[0194] Positioning mode Network device execution function Terminal equipment execution function 1 Model Training Model predictions 2 Model training, model prediction 3 Model training, model prediction

[0195] In positioning mode 1, the terminal device has certain computing power and storage capacity, which can perform model prediction, but it is not enough for model training, so the network device performs the model training process. After the network device trains the positioning model, it can send the positioning model and the environmental information of the environment where the terminal device is located to the terminal device for model prediction.

[0196] In positioning mode 2, the computing power or storage capacity of the terminal device is relatively low and insufficient for model prediction, so the network device performs the model training process and the model prediction process. After the network device predicts the positioning information of the terminal device, it can send it to the terminal device.

[0197] In positioning mode 3, the terminal device has strong computing and storage capabilities and can perform model training, so the terminal device can perform model training and model prediction. The network device can send model training data (which may include the initial prediction model and the first training sample data) and environmental information of the environment area where the terminal device is located to the terminal device for the terminal device to perform model training and model prediction.

[0198] For the terminal device to be located, its positioning mode can be determined based on the above method; in order to obtain a better positioning mode determination result, in some embodiments, the positioning mode can also be determined in combination with other factors.

[0199] For example, the positioning mode can be determined in combination with the current communication status. When the communication status is not good, the positioning mode of the terminal device can be adjusted. For example, when the terminal device's capabilities meet the computing power and storage capacity required by positioning mode 1, if the downlink communication status is poor (for example, congestion occurs), the network device can also perform a mode prediction process, that is, the positioning mode of the terminal device can be adjusted to positioning mode 2; when the terminal device's capabilities meet the computing power and storage capacity required by positioning mode 3, if the downlink communication status is not good, the network device can also perform a model training process, or, perform a model training process and a mode prediction process at the same time, that is, the positioning mode of the terminal device can be adjusted to positioning mode 1 or positioning model 2 according to the communication status. For the sake of convenience, the embodiments of the present application are subsequently described by taking the method of determining the positioning mode based only on the computing power and storage capacity of the terminal device as an example.

[0200] It can be understood that the naming method of some terms in the embodiments of the present application is only an example and should not be understood as a limitation on the embodiments of the present application. In some embodiments, the same terms may also be named by other names, for example, positioning mode 1, positioning mode 2, positioning mode 3, which may also be referred to as the first positioning mode, the second positioning mode, and the third positioning mode, respectively.

[0201] The positioning processes in these three positioning modes are described in detail below.

[0202] Positioning Mode 1

[0203] Figure 7 A schematic diagram of the positioning process corresponding to positioning mode 1 provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the positioning process may include the following steps:

[0204] S101. The terminal device reports capability information to the network device.

[0205] The capability information may indicate the computing power and storage capacity of the terminal device that can be used for positioning.

[0206] The computing power of the terminal device that can be used for positioning can be determined based on the remaining computing power of the terminal device, or based on the remaining computing power of the terminal device and the computing power that can be released. Specifically, the program / application that can be suspended or terminated can be determined based on the priority or other information of the program / application on the terminal device, thereby determining the computing power that can be released by the terminal device.

[0207] In the case where the computing power that can be used for positioning is determined based on the remaining computing power and the releasable computing power, when the terminal device reports the capability information related to the computing power, it can be the remaining computing power and the releasable computing power, and the network device will calculate the computing power that the terminal device can use for positioning; or it can be the computing power that can be used for positioning that is calculated based on the remaining computing power and the releasable computing power, and the calculation result will be reported to the network device.

[0208] It can be understood that in some embodiments, a portion of computing power can also be reserved for the terminal device to improve the performance of the terminal device. For example, after the terminal device determines the remaining computing power, or calculates the sum of the remaining computing power and the releasable computing power, it can subtract the reserved computing power to obtain the computing power that the terminal device can use for positioning; alternatively, the network device can calculate the computing power that the terminal device can use for positioning based on the reserved computing power.

[0209] Similar to computing power, the storage capacity of the terminal device that can be used for positioning can be determined based on the remaining storage space of the terminal device, or based on the remaining storage space and releasable storage space of the terminal device. For example, a portion of the cache can be cleared on the terminal device, or the terminal device may store previously acquired positioning models, training sample data, and / or environmental information of the current environmental area. In this case, the content of this portion of the storage space can be overwritten and updated, and the storage space can also be used as releasable storage space.

[0210] Similarly, in the case where the storage capacity that can be used for positioning is determined based on the remaining storage capacity and the releasable storage capacity, when the terminal device reports the capability information related to the storage capacity, it can be the remaining storage capacity and the releasable storage capacity, and the network device will calculate the storage capacity that the terminal device can use for positioning; or it can be the case that the storage capacity that can be used for positioning is calculated based on the remaining storage capacity and the releasable storage capacity, and the calculation result is reported to the network device.

[0211] In some embodiments, a portion of storage capacity may also be reserved for the terminal device to improve the performance of the terminal device. For example, after the terminal device determines the remaining storage capacity, or calculates the sum of the remaining storage capacity and the releasable storage capacity, it can subtract the reserved storage capacity to obtain the storage capacity that the terminal device can use for positioning; alternatively, the network device can calculate the storage capacity that the terminal device can use for positioning based on the reserved storage capacity.

[0212] In actual applications, the terminal device can report capability information to the currently connected network device when positioning is required; in some embodiments, if the capability information has been reported to the network device before, the terminal device can also report the capability information to the currently connected network device when the time since the last capability information was reported reaches a certain length of time, so as to save communication resources.

[0213] In some embodiments, the terminal device may also report capability information to a network device when first connecting to the network device; or, the terminal device may also report capability information to the network device after receiving a capability reporting notification from the network device.

[0214] It is understandable that the case where the terminal device reports capability information is not limited to the above examples, and the embodiment of the present application does not specifically limit when to report the capability information.

[0215] S102: The network device determines that the positioning mode of the terminal device is positioning mode 1 according to the capability information.

[0216] After receiving the capability information reported by the terminal device, the network device can determine the positioning mode of the terminal device according to the capability information of the terminal device and the capability information required by various positioning modes.

[0217] As mentioned above, when the terminal device has certain computing power and storage capacity and can perform model prediction, but is insufficient for model training, the network device can determine that the positioning mode of the terminal device is positioning mode 1; when the computing power of the terminal device is relatively low, or the storage capacity is relatively low and insufficient for model prediction, the positioning mode of the terminal device is determined to be positioning mode 2; when the computing power and storage capacity of the terminal device are strong and model training can be performed, the positioning mode of the terminal device is determined to be positioning mode 3.

[0218] Exemplarily here, the positioning mode of the terminal device determined by the network device is positioning mode 1.

[0219] S103: The network device sends a mode notification message to the terminal device.

[0220] After determining the positioning mode of the terminal device, the network device may send a message (ie, a mode notification message) indicating the positioning mode of the terminal device to the terminal device so that the terminal device can learn its positioning mode.

[0221] It can be understood that in some embodiments, the network device may not send a mode notification message to the terminal device, and the terminal device may determine its positioning mode based on other messages sent by the network device. For example, after receiving the positioning model sent by the network device, it may determine that its positioning mode is positioning mode 1.

[0222] S104: The network device uses the first training data to train an initial prediction model to obtain a positioning model.

[0223] When the positioning mode of the terminal device is positioning mode 1, the network device performs a model training process and the terminal device performs a model prediction process, wherein the way in which the network device uses the first training data to train the initial prediction model can be found in the relevant description in the aforementioned step S200 and will not be repeated here.

[0224] It should be noted that the network device may perform a model training process in advance, and the process of training the model by the network device may be executed after determining the positioning mode of the terminal device, or may be executed at any other time.

[0225] S105: The network device sends the positioning model and environmental information of the environment area where the terminal device is located to the terminal device.

[0226] After the network device obtains the positioning model through training, it can send it to the terminal device, and can also send the environmental information of the current environment area where the terminal device is located to the terminal device for the terminal device to perform model prediction.

[0227] Among them, the network device can determine the approximate location of the terminal device according to the message sent by the terminal device when reporting the capability information, through the information carried in the message (such as the cell identifier) ​​or through angle measurement and ranging, thereby determining the environmental area where the terminal device is located. The method for obtaining the environmental information of the environmental area where the terminal device is located can refer to the relevant description in the aforementioned step S100, which will not be repeated here.

[0228] After the terminal device receives the positioning model and environmental information sent by the network device, it can predict its own position (i.e., positioning information) based on the CSI information, environmental information and positioning model.

[0229] As mentioned above, the CSI information can be uplink CSI information or downlink CSI information; the CSI information used for predicting the positioning information can be of the same type as the CSI information used for training the positioning model to improve the accuracy of the positioning result. Here, for example, the training sample data used by the network device to train the positioning model is determined based on the uplink CSI information, and the terminal device can perform the following step S106 to send an uplink RS to obtain the uplink CSI information.

[0230] It can be understood that in some embodiments, the training sample data used by the network device to train the positioning model can also be determined based on the downlink CSI information. Then, the network device can carry the downlink RS when sending the positioning model, and the terminal device can also request the network device to send the downlink RS when positioning is needed. Then, the terminal device can determine the downlink CSI information based on the downlink RS, and input the downlink CSI information and environmental information into the positioning model to obtain the positioning information of the terminal device.

[0231] In other embodiments, the training sample data used by the network device to train the positioning model may also be determined partly based on the uplink CSI information and partly based on the downlink CSI information. In this case, the uplink CSI information or the downlink CSI information can be used to predict the positioning information of the terminal device. The subsequent embodiments are similar and will not be repeated here.

[0232] S106. The terminal device sends an uplink RS to the network device.

[0233] When the terminal device needs to be positioned, the terminal device can send an uplink RS to the network device.

[0234] S107. The network device sends CSI information determined based on the uplink RS to the terminal device.

[0235] After the network device receives the uplink RS sent by the terminal device, it can determine the CSI information based on the uplink RS, and then send it to the terminal device.

[0236] It is understandable that there may be a certain delay from the time when the terminal device sends the uplink RS to the time when the network device sends the CSI information to the terminal device. Therefore, when the network device sends the CSI information, it can carry a timestamp, which can be the time when the terminal device sends the uplink RS; considering that the transmission time of the uplink RS between the terminal device and the network device is very short and can be ignored, in some embodiments, the timestamp can also be the time when the network device receives the uplink RS. Subsequently, after the terminal device receives the CSI information, it can know at what time the predicted positioning information is the positioning information of the terminal device based on the timestamp.

[0237] S108. The terminal device inputs the CSI information and the environmental information into the positioning model to obtain the positioning information of the terminal device.

[0238] After the terminal device receives the CSI information sent by the network device, it can input the CSI information and the environmental information of the current environmental area into the positioning model for position prediction to obtain the positioning information of the terminal device.

[0239] In positioning mode 1, the model prediction process is performed on the terminal device side, which helps to protect the privacy of the terminal device. After the terminal device predicts the positioning information, it can report its positioning information to the network device or not; in some embodiments, the terminal device can decide whether to report its positioning information according to its own privacy requirements.

[0240] It can be understood that in some embodiments, after the terminal device obtains the positioning model and the environmental information of a certain environmental area and performs positioning, within a period of time (referred to as the first time period here), if it wants to perform positioning in the environmental area again, it can skip the above step S101 and directly execute step S106 to send an uplink RS to the network device or request the network device to send a downlink RS, and perform positioning according to the determined CSI information, the environmental information of the environmental area and the positioning model to save communication resources; when the first time period is exceeded, the terminal device can execute the above step S101 to update the positioning model and the environmental information of the environmental area, or the terminal device can request environmental information from the network device without requesting the positioning model within the second time period after obtaining the positioning model, and only update the environmental information of the environmental area without updating the positioning model, so as to further save communication resources.

[0241] The specific durations of the first duration and the second duration can be set according to actual needs, and the embodiments of the present application do not specifically limit this. Considering that the update cycle of the model is relatively long, in some embodiments, the second duration can be greater than the first duration.

[0242] As mentioned above, after the initial prediction model is trained to obtain the positioning model, the second training sample data can be obtained to update the trained positioning model. In some embodiments, the training samples in the second training sample data can be generated by the following steps S109 and S110. In this embodiment, the generation of training samples based on uplink CSI information is used as an example for illustrative explanation; in some embodiments, the network device may send a downlink RS to the terminal device, and after the terminal device determines the downlink CSI information based on the downlink RS, the downlink CSI information and the location information of the terminal device are sent to the network device for the network device to generate training samples.

[0243] S109. The terminal device sends the first RS and location information of the terminal device to the network device.

[0244] The first RS is the RS sent by the terminal device to the network device and can be used to generate training samples; the location information of the terminal device can be location information determined by other positioning methods, for example, it can be location information determined by GPS positioning technology.

[0245] It is understandable that when the terminal device sends the first RS and the location information, it may be sent through multiple data packets. At this time, the terminal device can carry a timestamp in the data packet so that the network device can establish a corresponding relationship between the first RS and the location information through the timestamp. In other steps of the embodiment of the present application, there may also be a situation where the amount of data to be sent is large and needs to be sent through multiple data packets. In these cases, time alignment can be performed by carrying a timestamp, so that the receiving end determines the corresponding relationship between the received data based on the timestamp.

[0246] In an embodiment of the present application, the terminal device may send the first RS and location information to the network device once at regular intervals, or may return the first RS and location information to the network device after receiving a request from the network device, or may send the first RS and location information in other circumstances. The embodiment of the present application does not specifically limit this.

[0247] S110. After determining the first CSI information according to the first RS, the network device generates a training sample in the second training sample data according to the first CSI information and the location information of the terminal device.

[0248] After the network device receives the first RS and location information sent by the terminal device, it can determine the CSI information (i.e., the first CSI information) based on the first RS, and then can use the first CSI information and the environmental information of the environmental area where the terminal device is currently located as input data for the training sample, and use the location information of the terminal device as the label data of the training sample to generate the training sample in the second training sample data.

[0249] S111. The network device uses the second training sample data to train and update the positioning model.

[0250] After collecting a certain amount of second training sample data, the network device may use the second training sample data to train and update the positioning model.

[0251] Positioning Mode 2

[0252] Figure 8 A schematic diagram of the positioning process corresponding to positioning mode 2 provided in the embodiment of the present application, such as Figure 8 As shown, the positioning process may include the following steps:

[0253] S201. The terminal device reports capability information to the network device.

[0254] The description of this step can refer to the relevant description of the above step S101, which will not be repeated here.

[0255] S202: The network device determines that the positioning mode of the terminal device is positioning mode 2 according to the capability information.

[0256] The process of the network device determining the positioning mode can refer to the relevant description in the above step S102, which will not be repeated here.

[0257] Here, illustratively, the positioning mode of the terminal device determined by the network device is positioning mode 2.

[0258] S203: The network device sends a mode notification message to the terminal device.

[0259] The description of this step can refer to the relevant description of the above step S103, which will not be repeated here.

[0260] S204: The network device uses the first training data to train an initial prediction model to obtain a positioning model.

[0261] The description of this step can refer to the relevant description of the above step S104, which will not be repeated here.

[0262] When the positioning mode of the terminal device is positioning mode 2, the network device performs a model training process and a model prediction process. After the network device obtains the positioning model through training, it can predict the location of the terminal device (i.e., positioning information) based on the CSI information, pre-built environmental information, and the positioning model.

[0263] Similarly, the CSI information can be uplink CSI information or downlink CSI information; the CSI information used for predicting the positioning information can be of the same type as the CSI information used for training the positioning model to improve the accuracy of the positioning result. Here, for example, the training sample data used by the network device to train the positioning model is determined based on the uplink CSI information, then the terminal device can execute the following step S205 to send an uplink RS for the network device to obtain the uplink CSI information, or, in some embodiments, the terminal device can also carry an uplink RS when reporting capability information, and the network device can determine the uplink CSI information accordingly.

[0264] It can be understood that in some embodiments, the training sample data used by the network device to train the positioning model can also be determined based on the downlink CSI information. The network device can send a downlink RS to the terminal device, and the terminal device can determine the downlink CSI information based on the downlink RS and report the downlink CSI information to the network device.

[0265] S205. The terminal device sends an uplink RS to the network device.

[0266] When the terminal device needs to be positioned, the terminal device can send an uplink RS to the network device.

[0267] S206: After determining the CSI information according to the uplink RS, the network device inputs the CSI information and the environmental information into the positioning model to obtain the positioning information of the terminal device.

[0268] After the network device receives the uplink RS sent by the terminal device, it can determine the CSI information based on the uplink RS, and then input the CSI information and the environmental information of the environmental area where the terminal device is located into the positioning model to obtain the positioning information of the terminal device.

[0269] S207: The network device sends the location information of the terminal device to the terminal device.

[0270] After predicting the location information of the terminal device, the network device may send the location information to the terminal device. In some embodiments, the network device may not send the location information to the terminal device, which may be determined according to actual needs.

[0271] It is understandable that in some embodiments, after a terminal device has reported capability information to a network device, when positioning is needed again within a period of time, it may not report the capability information to the network device again and directly perform the subsequent model prediction process to save communication resources.

[0272] Positioning Mode 3

[0273] Fig. 9A schematic diagram of the positioning process corresponding to positioning mode 3 provided in the embodiment of the present application, such as Fig. 9 As shown, the positioning process may include the following steps:

[0274] S301. The terminal device reports capability information to the network device.

[0275] The description of this step can refer to the relevant description of the above step S101, which will not be repeated here.

[0276] S302: The network device determines the positioning mode of the terminal device according to the capability information.

[0277] The process of the network device determining the positioning mode can refer to the relevant description in the above step S102, which will not be repeated here.

[0278] Here, illustratively, the positioning mode of the terminal device determined by the network device is positioning mode 3.

[0279] S303: The network device sends a mode notification message to the terminal device.

[0280] The description of this step can refer to the relevant description of the above step S103, which will not be repeated here.

[0281] S304: The network device sends an initial prediction model and first training sample data to the terminal device.

[0282] When the positioning mode of the terminal device is positioning mode 3, the terminal device performs a model training process and a model prediction process. After determining the positioning mode of the terminal device, the network device can send an initial prediction model and a first training sample data to the terminal device for the terminal device to perform model training and model prediction.

[0283] S305: The terminal device uses the first training sample data to train an initial prediction model to obtain a positioning model.

[0284] After receiving the initial prediction model and the first training sample data sent by the network device, the terminal device can use the first training sample data to train the initial prediction model to obtain a positioning model. The manner in which the terminal device uses the first training data to train the initial prediction model can refer to the relevant description in the aforementioned step S200, which will not be repeated here.

[0285] After the terminal device obtains the positioning model through training, it can predict its own position (i.e. positioning information) based on the CSI information, environmental information and positioning model.

[0286] As mentioned above, the CSI information can be uplink CSI information or downlink CSI information; the CSI information used for predicting the positioning information can be of the same type as the CSI information used for training the positioning model to improve the accuracy of the positioning result. Here, for example, the training sample data used by the terminal device to train the positioning model is determined based on the downlink CSI information, and the terminal device can execute the following step S306 to send a positioning request to obtain the downlink RS and then obtain the downlink CSI information.

[0287] It can be understood that in some embodiments, the training sample data used by the terminal device to train the positioning model can also be determined based on the uplink CSI information. The terminal device can send an uplink RS to the network device when positioning is required, and then the network device can determine the uplink CSI information based on the uplink RS and return the uplink CSI information to the terminal device.

[0288] S306: The terminal device sends a positioning request to the network device.

[0289] When the terminal device needs to be located, the terminal device can send a positioning request to the network device.

[0290] S307: The network device sends the downlink RS and environmental information of the environment area where the terminal device is located to the terminal device.

[0291] After receiving the positioning request sent by the terminal device, the network device can send the downlink RS and the environmental information of the environmental area where the terminal device is located to the terminal device. In some embodiments, the process of sending the environmental information of the environmental area where the terminal device is located to the terminal device can also be performed after the network device determines that the positioning mode of the terminal device is positioning mode 3 and before the terminal device sends a positioning request to the network device.

[0292] S308. After the terminal device determines the CSI information according to the downlink RS, the CSI information and the environmental information are input into the positioning model to obtain the positioning information of the terminal device.

[0293] After receiving the downlink RS sent by the network device, the terminal device can determine the CSI information based on the downlink RS, and then input the CSI information and the environmental information of the environmental area where the terminal device is located into the positioning model to obtain the positioning information of the terminal device.

[0294] In positioning mode 3, both model training and model prediction processes are performed on the terminal device side, which is more conducive to the privacy protection of the terminal device. After the terminal device predicts the positioning information, it can report its positioning information to the network device or not; in some embodiments, the terminal device can decide whether to report its positioning information according to its own privacy requirements.

[0295] Similar to step S108, in some embodiments, after the terminal device obtains the positioning model and the environmental information of a certain environmental area and performs positioning, if it wants to position itself in the environmental area again within a first time period, it can skip the above steps S301 and S305 to save communication resources and processing resources; when the first time period is exceeded, the terminal device can execute the above step S301 to update the positioning model and the environmental information of the environmental area, or the terminal device can request environmental information from the network device without requesting the positioning model within a second time period after obtaining the positioning model, and only update the environmental information of the environmental area without updating the positioning model, so as to further save communication resources.

[0296] As mentioned above, after the initial prediction model is trained to obtain the positioning model, the second training sample data can be obtained to update the trained positioning model. In some embodiments, the training samples in the second training sample data can be generated by the following steps S309 and S310. In this embodiment, the generation of training samples based on downlink CSI information is used as an example for illustrative explanation; in some embodiments, the terminal device may send an uplink RS to the network device, and after the network device determines the CSI information based on the uplink RS, the CSI information is sent to the terminal device for the terminal device to generate training samples.

[0297] S309: The network device sends a second RS to the terminal device.

[0298] Among them, the second RS is the RS sent by the network device to the terminal device and can be used to generate training samples; the network device can send the second RS to the terminal device once every period of time, or return the second RS to the terminal device after receiving a request from the terminal device, or can send the second RS in other situations, and the embodiments of the present application do not specifically limit this.

[0299] S310. After the terminal device determines the second CSI information according to the second RS, it generates a training sample in the second training sample data according to the second CSI information and the location information of the terminal device.

[0300] After the terminal device receives the second RS sent by the network device, it can determine the CSI information (i.e., the second CSI information) based on the second RS; then the second CSI information and the environmental information of the environmental area where the terminal device is currently located can be used as input data of the training sample, and the location information of the terminal device can be used as the label data of the training sample to generate the training sample in the second training sample data.

[0301] The environmental information of the environment area where the terminal device is currently located may be the most recently acquired by the terminal device. In some embodiments, the network device may also send the environmental information of the environment area where the terminal device is currently located in addition to sending the second RS.

[0302] The location information of the terminal device may be location information determined by other positioning methods, for example, it may be location information determined by using GPS positioning technology.

[0303] S311. The terminal device uses the second training sample data to train and update the positioning model.

[0304] After collecting a certain amount of second training sample data, the terminal device can use the second training sample data to train and update the positioning model.

[0305] Those skilled in the art will appreciate that the above embodiments are exemplary and are not intended to limit the present application. Where possible, the execution order of one or more of the above steps may be adjusted, or may be selectively combined to obtain one or more other embodiments. For example, in some embodiments, a pattern determination process, a model training process, and / or a model update process may not be included. Those skilled in the art may select and combine any of the above steps as needed, and all that do not depart from the essence of the present application scheme shall fall within the scope of protection of the present application.

[0306] The positioning method provided in the embodiment of the present application, when positioning a terminal device, inputs the CSI information between the network device and the terminal device and the environmental information of the environmental area where the terminal device is located into a trained positioning model to obtain the positioning information of the terminal device, wherein the positioning model is pre-trained using training sample data of multiple environmental areas, so that the positioning model can learn the correlation between the positioning information, CSI information and environmental information, and the predicted positioning information is related to the CSI information and the environmental information at the same time, thereby improving the accuracy of the prediction result, that is, improving the positioning accuracy; and the positioning model can be used to predict the positioning information of terminal devices in different environmental areas, thereby improving the versatility of the model and reducing the positioning cost.

[0307] Based on the same concept, as an implementation of the above method, an embodiment of the present application provides a communication device, and the device embodiment corresponds to the above method embodiment. For ease of reading, the present device embodiment will no longer repeat the details of the above method embodiment one by one, but it should be clear that the device in this embodiment can correspond to all the contents in the above method embodiment.

[0308] Fig.10 A schematic diagram of the structure of a communication device provided in an embodiment of the present application, such as Fig.10As shown, the device provided in this embodiment includes: a transceiver module 110 and a processing module 120 .

[0309] In a possible implementation, the communication device is used to execute each process and step corresponding to the network device in the above method embodiment.

[0310] The processing module 120 is used to obtain environmental information of the environment area where the terminal device to be located is located;

[0311] The processing module 120 is also used to input the CSI information and environmental information between the network device and the terminal device into the trained positioning model to obtain the positioning information of the terminal device, wherein the positioning model is pre-trained using training sample data from multiple environmental areas.

[0312] Optionally, the processing module 120 is specifically used to: when the positioning mode of the terminal device is the first positioning mode, after acquiring the environmental information, instruct the transceiver module 110 to send the positioning model and the environmental information to the terminal device, so that the CSI information and the environmental information are input into the positioning model through the terminal device to obtain the positioning information of the terminal device;

[0313] The transceiver module 110 is also used for: when the positioning mode of the terminal device is the second positioning mode, the processing module 120 inputs the CSI information and the environmental information into the positioning model, and after obtaining the positioning information of the terminal device, sends the positioning information to the terminal device.

[0314] Optionally, the training sample data used by the network device to train the positioning model is determined based on uplink CSI information;

[0315] The transceiver module 110 is also used to: receive an uplink RS sent by a terminal device;

[0316] The processing module 120 is further used to: determine CSI information according to the uplink RS;

[0317] The transceiver module 110 is further used to send CSI information to the terminal device when the positioning mode of the terminal device is the first positioning mode.

[0318] Optionally, the processing module 120 is further configured to:

[0319] Before inputting CSI information and environmental information into the positioning model, first training sample data is used to train the initial prediction model to obtain the positioning model, and the first training sample data includes training sample data of multiple environmental areas.

[0320] Optionally, the processing module 120 is further configured to:

[0321] After the initial prediction model is trained to obtain the positioning model, the second training sample data is used to train and update the positioning model, and the second training sample data includes training sample data of at least one environmental area.

[0322] Optionally, the transceiver module 110 is further used to: receive a first RS and location information of the terminal device sent by the terminal device;

[0323] The processing module 120 is further configured to: after determining the first CSI information according to the first RS; generate a training sample in the second training sample data according to the first CSI information and the location information of the terminal device.

[0324] Optionally, the processing module 120 is specifically used to: when the positioning mode of the terminal device is the third positioning mode, after obtaining the environmental information, instruct the transceiver module 110 to send the environmental information to the terminal device, so as to input the CSI information and the environmental information into the positioning model through the terminal device to obtain the positioning information of the terminal device, wherein the positioning model is obtained by training the terminal device.

[0325] Optionally, the training sample data used by the terminal device to train the positioning model is determined based on the downlink CSI information; the transceiver module 110 is further used to:

[0326] Before the processing module 120 inputs the CSI information and the environment information into the positioning model through the terminal device, after receiving the positioning request sent by the terminal device, a downlink RS is sent to the terminal device, and the downlink RS is used by the terminal device to determine the CSI information.

[0327] Optionally, the transceiver module 110 is also used to: before sending environmental information to the terminal device, send an initial prediction model and first training sample data to the terminal device, the first training sample data including training samples of multiple environmental areas, which are used by the terminal device to train the initial prediction model to obtain a positioning model.

[0328] Optionally, the transceiver module 110 is also used to: after sending the initial prediction model to the terminal device, send a second RS to the terminal device, the second RS is used for the terminal device to generate training samples in second training sample data, so as to train and update the positioning model based on the second training sample data.

[0329] Optionally, the transceiver module 110 is further used to: receive capability information sent by the terminal device, where the capability information is used to indicate the computing capability and storage capability of the terminal device that can be used for positioning;

[0330] The processing module 120 is further used to determine the positioning mode of the terminal device according to the capability information.

[0331] Optionally, the transceiver module 110 is further used to send a message indicating a positioning mode to the terminal device.

[0332] Optionally, the environmental information includes: spatial position information of each scatterer in the environmental area where the terminal device is located.

[0333] In another possible implementation, the communication device is used to execute each process and step corresponding to the terminal device in the above method embodiment.

[0334] The transceiver module 110 is used to receive the environment information of the environment area where the terminal device is located sent by the network device;

[0335] The processing module 120 is used to input the CSI information and environmental information between the network device and the terminal device into the trained positioning model to obtain the positioning information of the terminal device, wherein the positioning model is pre-trained using training sample data of multiple environmental areas.

[0336] Optionally, the transceiver module 110 is specifically used to: when the positioning mode of the terminal device is the first positioning mode, receive the positioning model sent by the network device and the environmental information of the environmental area where the terminal device is located; the processing module 120 is specifically used to: input the CSI information and the environmental information into the positioning model received by the transceiver module 110 to obtain the positioning information of the terminal device;

[0337] The transceiver module 110 is also used to: when the positioning mode of the terminal device is the second positioning mode, receive the positioning information of the terminal device sent by the network device, and the positioning information sent by the network device is obtained by the network device inputting CSI information and environmental information into the positioning model.

[0338] Optionally, the positioning model is obtained by training the network device, and the training sample data used by the network device to train the positioning model is determined based on the uplink CSI information; the transceiver module 110 is further used for:

[0339] Sending an uplink RS to a network device, where the uplink RS is used by the network device to determine CSI information;

[0340] When the positioning mode of the terminal device is the first positioning mode, CSI information sent by the network device is received.

[0341] Optionally, the positioning model is obtained by the network device using the first training sample data to train an initial prediction model, and the transceiver module 110 is further used for:

[0342] The first RS and the location information of the terminal device are sent to the network device, and the first RS is used by the network device to generate training samples in the second training sample data, so as to train and update the positioning model based on the second training sample data.

[0343] Optionally, the transceiver module 110 is further used to: when the positioning mode of the terminal device is the third positioning mode, before the processing module 120 inputs the CSI information and the environmental information into the positioning model, receive the initial prediction model and the first training sample data sent by the network device, the first training sample data including the training sample data of multiple environmental areas;

[0344] The processing module 120 is further used to: use the first training sample data to train the initial prediction model to obtain a positioning model.

[0345] Optionally, the training sample data used by the terminal device to train the positioning model is determined based on the downlink CSI information; the transceiver module 110 is also used to: send a positioning request to the network device before the processing module 120 inputs the CSI information and the environmental information into the positioning model; receive the downlink RS sent by the network device;

[0346] The processing module 120 is further configured to determine CSI information according to the downlink RS.

[0347] Optionally, the processing module 120 is further used to: after training the initial prediction model to obtain the positioning model, use second training sample data to train and update the positioning model, and the second training sample data includes training sample data of at least one environmental area.

[0348] Optionally, the transceiver module 110 is further configured to: receive a second RS sent by the network device;

[0349] The processing module 120 is further used to: after determining the second CSI information according to the second RS; generate a training sample in the second training sample data according to the second CSI information and the location information of the terminal device.

[0350] Optionally, the transceiver module 110 is further configured to:

[0351] Sending capability information to the network device, the capability information is used to indicate the computing capability and storage capability of the terminal device that can be used for positioning;

[0352] A message sent by a network device to indicate a positioning mode of a terminal device is received, where the positioning mode is determined by the network device according to capability information.

[0353] Optionally, the environmental information includes: spatial position information of each scatterer in the environmental area where the terminal device is located.

[0354] Furthermore, the communication device may also include a storage module, which can be used to store instructions executed by the transceiver module 110 and the processing module 120, as well as the model, training sample data and environmental information described in the above method embodiment.

[0355] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0356] An embodiment of the present application also provides a communication device. Fig.11 A schematic diagram of the structure of a communication device provided in an embodiment of the present application, optionally for the sake of convenience of explanation, Fig.11 Only the main components of the communication device are shown. Fig.11 As shown, the communication device provided in this embodiment includes: a processor 210, a memory 220 and a transceiver 230. The processor 210, the memory 220 and the transceiver 230 communicate with each other through an internal connection path.

[0357] In a possible implementation, the communication device is used to execute each process and step corresponding to the network device in the above method.

[0358] In another possible implementation, the communication device is used to execute each process and step corresponding to the terminal device in the above method.

[0359] It should be understood that the communication device may specifically be the terminal device or network device in the above embodiments, and may be used to execute the various steps and / or processes corresponding to the terminal device or network device in the above method embodiments.

[0360] The processor 210 can be used to execute instructions stored in the memory 220, and when the processor 210 executes the instructions stored in the memory 220, the processor 210 is used to execute the various steps and / or processes of the above-mentioned method embodiment corresponding to the terminal device or network device.

[0361] The memory 220 may be used to store instructions, software programs, and data, such as the model, training sample data, and environmental information described in the above method embodiments.

[0362] The transceiver 230 may include a transmitter and a receiver, wherein the transmitter may be used to implement the various steps and / or processes corresponding to the above-mentioned transceiver for performing the sending action, and the receiver may be used to implement the various steps and / or processes corresponding to the above-mentioned transceiver for performing the receiving action.

[0363] Those skilled in the art will appreciate that for ease of description, Fig.11 Only one memory 220 and processor 210 are shown. In an actual communication device, there may be multiple processors 210 and memories 220. The memory 220 may also be referred to as a storage medium or a storage device, etc., which is not limited in the embodiments of the present application.

[0364] For example, the processor 210 may include a baseband processor and a central processing unit. The baseband processor is mainly used to process the communication protocol and communication data, and the central processing unit is mainly used to control the entire terminal device, execute software programs, and process data of the software programs. Fig.11 The processor 210 in the embodiment integrates the functions of the baseband processor and the central processing unit. It can be understood by those skilled in the art that the baseband processor and the central processing unit can also be independent processors, which are interconnected through technologies such as buses. It can be understood by those skilled in the art that the communication device can include multiple baseband processors to adapt to different network formats, and the communication device can include multiple central processing units to enhance its processing capabilities. The various components of the communication device can be connected through various buses. The baseband processor can also be described as a baseband processing circuit or a baseband processing chip. The central processing unit can also be described as a central processing circuit or a central processing chip. The function of processing the communication protocol and the communication data can be built into the processor 210, or it can be stored in the storage unit in the form of a software program, and the processor 210 executes the software program to implement the baseband processing function.

[0365] It should be understood that in the embodiment of the present application, the processor 210 may be a central processing unit (CPU), and the processor 210 may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0366] It should also be understood that the memory 220 in the embodiment of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an EPROM, an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous connection dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0367] The communication device provided in this embodiment can execute each step and / or process corresponding to the terminal device or network device in the above method embodiment, and its implementation principle and technical effect are similar and will not be repeated here.

[0368] An embodiment of the present application also provides a communication system, including the aforementioned network device and terminal device.

[0369] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method described in the above method embodiment is implemented.

[0370] The embodiment of the present application also provides a computer program product. When the computer program product is run on a communication device, the communication device implements the method described in the above method embodiment when executing the computer program product.

[0371] The present application also provides a chip system, including a processor, the processor is coupled to a memory, and the processor executes a computer program stored in the memory to implement the method described in the above method embodiment. The chip system can be a single chip or a chip module composed of multiple chips.

[0372] 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 may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk or a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0373] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media can include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

[0374] The naming or numbering of the steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The named or numbered process steps can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0375] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0376] In the embodiments provided in the present application, it should be understood that the disclosed devices / equipment and methods can be implemented in other ways. For example, the device / equipment embodiments described above are merely schematic, for example, the division of the modules or units is only a logical function division, and there may be other division methods in actual implementation, 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.

[0377] It should be understood that in the description of the present application specification and the appended claims, the terms "include", "comprises", "have" and any variations thereof are intended to cover non-exclusive inclusions and mean "including but not limited to", unless otherwise specifically emphasized. For example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0378] In the description of this application, unless otherwise specified, " / " indicates that the objects associated with each other are in an "or" relationship. For example, A / B can represent A or B. "And / or" in this application is used to describe the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.

[0379] Furthermore, in the description of this application, unless otherwise specified, "plurality" means two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0380] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0381] In addition, in the description of the present specification and the appended claims, the terms "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein; the features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0382] In the embodiments of the present application, the words "exemplarily" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0383] References to "one embodiment" or "some embodiments" etc. described in the specification of the present application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in the specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, not to limit them; although the present application has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A positioning method, applied to a network device, characterized in that: The method comprises: Obtaining environmental information of the environment area where the terminal device to be located is located; The CSI information between the network device and the terminal device and the environmental information are input into a trained positioning model to obtain the positioning information of the terminal device, wherein the positioning model is pre-trained using training sample data of multiple environmental areas.

2. The method according to claim 1, characterized in that In a case where the positioning mode of the terminal device is the first positioning mode, the network device sends the positioning model and the environmental information to the terminal device after acquiring the environmental information, and the terminal device inputs the CSI information and the environmental information into the positioning model to obtain the positioning information of the terminal device; When the positioning mode of the terminal device is the second positioning mode, the network device inputs the CSI information and the environmental information into the positioning model, obtains the positioning information of the terminal device, and then sends the positioning information to the terminal device.

3. The method according to claim 2, characterized in that The training sample data used by the network device to train the positioning model is determined based on uplink CSI information; before the CSI information and the environmental information are input into the positioning model, the method further includes: Receiving an uplink RS sent by the terminal device; Determine the CSI information according to the uplink RS; When the positioning mode of the terminal device is the first positioning mode, the CSI information is sent to the terminal device.

4. The method according to claim 2 or 3, characterized in that: Before inputting the CSI information and the environment information into the positioning model, the method further includes: The initial prediction model is trained using first training sample data to obtain the positioning model, wherein the first training sample data includes training sample data of multiple environmental areas.

5. The method according to claim 4, characterized in that After the initial prediction model is trained to obtain the positioning model, the method further includes: The positioning model is trained and updated using second training sample data, where the second training sample data includes training sample data of at least one environmental area.

6. The method according to claim 5, characterized in that The method further comprises: Receiving a first RS and location information of the terminal device sent by the terminal device; Determine first CSI information according to the first RS; Generate training samples in the second training sample data according to the first CSI information and the location information of the terminal device.

7. The method according to any one of claims 1 to 6, characterized in that: When the positioning mode of the terminal device is the third positioning mode, the network device sends the environmental information to the terminal device after acquiring the environmental information, and inputs the CSI information and the environmental information into the positioning model through the terminal device to obtain the positioning information of the terminal device, wherein the positioning model is obtained by training the terminal device.

8. The method according to claim 7, characterized in that The training sample data used by the terminal device to train the positioning model is determined based on downlink CSI information; Before inputting the CSI information and the environment information into the positioning model through the terminal device, the method further includes: After receiving the positioning request sent by the terminal device, a downlink RS is sent to the terminal device, and the downlink RS is used by the terminal device to determine the CSI information.

9. The method according to claim 7 or 8, characterized in that: Before sending the environment information to the terminal device, the method further includes: An initial prediction model and first training sample data are sent to the terminal device, where the first training sample data includes training samples of multiple environmental areas and is used by the terminal device to train the initial prediction model to obtain the positioning model.

10. The method according to claim 9, characterized in that After sending the initial prediction model to the terminal device, the method further includes: A second RS is sent to the terminal device, where the second RS is used by the terminal device to generate training samples in second training sample data, so as to train and update the positioning model based on the second training sample data.

11. The method according to any one of claims 2 to 10, characterized in that: The method further comprises: receiving capability information sent by the terminal device, where the capability information is used to indicate computing capability and storage capability of the terminal device that can be used for positioning; A positioning mode of the terminal device is determined according to the capability information.

12. The method according to claim 11, characterized in that The method further comprises: A message indicating the positioning mode is sent to the terminal device.

13. The method according to any one of claims 1 to 12, characterized in that: The environmental information includes: spatial position information of each scatterer in the environmental area where the terminal device is located.

14. A positioning method, applied to a terminal device, characterized in that: The method comprises: Receiving environmental information of an environmental area where the terminal device is located, sent by a network device; The CSI information between the network device and the terminal device and the environmental information are input into a trained positioning model to obtain the positioning information of the terminal device, wherein the positioning model is pre-trained using training sample data of multiple environmental areas.

15. The method according to claim 14, characterized in that When the positioning mode of the terminal device is the first positioning mode, the terminal device receives the positioning model sent by the network device and the environmental information of the environment area where the terminal device is located, inputs the CSI information and the environmental information into the positioning model, and obtains the positioning information of the terminal device; When the positioning mode of the terminal device is the second positioning mode, the terminal device receives the positioning information of the terminal device sent by the network device, and the positioning information sent by the network device is obtained by the network device inputting the CSI information and the environmental information into the positioning model.

16. The method according to claim 15, characterized in that The positioning model is obtained by training the network device, and the training sample data used by the network device to train the positioning model is determined based on uplink CSI information; Before inputting the CSI information and the environment information into the positioning model, the method further includes: Sending an uplink RS to the network device, where the uplink RS is used by the network device to determine the CSI information; When the positioning mode of the terminal device is the first positioning mode, the CSI information sent by the network device is received.

17. The method according to claim 15 or 16, characterized in that The positioning model is obtained by the network device training an initial prediction model using first training sample data, and the method further includes: A first RS and location information of the terminal device are sent to the network device, wherein the first RS is used by the network device to generate training samples in second training sample data, so as to train and update the positioning model based on the second training sample data.

18. The method according to any one of claims 14 to 17, characterized in that: When the positioning mode of the terminal device is the third positioning mode, before inputting the CSI information and the environment information into the positioning model, the method further includes: Receiving an initial prediction model and first training sample data sent by the network device, where the first training sample data includes training sample data of multiple environmental areas; The first training sample data is used to train the initial prediction model to obtain a positioning model.

19. The method according to claim 18, characterized in that The training sample data used by the terminal device to train the positioning model is determined based on downlink CSI information; before the CSI information and the environmental information are input into the positioning model, the method further includes: Sending a positioning request to the network device; Receiving a downlink RS sent by the network device; The CSI information is determined according to the downlink RS.

20. The method according to claim 18 or 19, characterized in that After training the initial prediction model to obtain the positioning model, the method further includes: The positioning model is trained and updated using second training sample data, where the second training sample data includes training sample data of at least one environmental area.

21. The method according to claim 20, characterized in that The method further comprises: Receiving a second RS sent by the network device; Determine second CSI information according to the second RS; Generate training samples in second training sample data according to the second CSI information and the location information of the terminal device.

22. The method according to any one of claims 15 to 21, characterized in that: The method further comprises: Sending capability information to the network device, where the capability information is used to indicate computing capability and storage capability of the terminal device that can be used for positioning; A message sent by the network device to indicate a positioning mode of the terminal device is received, where the positioning mode is determined by the network device based on the capability information.

23. The method according to any one of claims 14 to 22, characterized in that: The environmental information includes: spatial position information of each scatterer in the environmental area where the terminal device is located.

24. A network device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to execute the method according to any one of claims 1 to 13 when calling the computer program.

25. A terminal device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to execute the method according to any one of claims 14 to 23 when calling the computer program.

26. A communication system, characterized in that: include: The network device as claimed in claim 24 and the terminal device as claimed in claim 25.

27. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 23 is implemented.

28. A computer program product, characterized in that When the computer program product runs on a communication device, the communication device is caused to execute the method according to any one of claims 1 to 23.

29. A chip system, characterized in that: The chip system includes a processor, which is coupled to a memory, and the processor executes a computer program stored in the memory to implement the method according to any one of claims 1-23.

Images