Object positioning method and object positioning device based on wireless device

Abstract

The present application provides an object positioning method and an object positioning device based on a wireless device. The method includes: obtaining multiple initial channel state information of multiple wireless devices in response to an indoor positioning instruction, wherein the initial channel state information represents device data related to a target object collected by the wireless device; for each initial channel state information, performing deviation elimination processing on the initial channel state information based on a preset deviation elimination formula to obtain target channel state information; generating multiple data combination matrices according to the multiple target channel state information, wherein each data combination matrix includes multiple matrix row and column values; for each data combination matrix, using a target encoder to process multiple matrix row and column values ​​and position encoding data of the wireless device corresponding to each matrix row and column value to generate a coordinate data set of the target object; performing weight fusion processing on the multiple coordinate data sets to obtain target positioning information of the target object.

Description

Technical Field

[0001] The present application relates to the technical field of data processing and neural network, and more specifically, to an object positioning method based on a wireless device, an object positioning device, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] As an indispensable device in modern life, wireless WiFi devices are widely used in the fields of communication and intelligent sensing. Under outdoor conditions, the Global Positioning System (GPS) can provide very accurate positioning and navigation services with the help of satellites. However, in indoor environments, due to the obstruction of buildings and the different environments in different buildings, the GPS system is no longer effective. Therefore, how to provide accurate and fast positioning services in indoor environments has attracted more and more attention from academia and industry.

[0003] Existing systems mainly use cameras to collect natural images and videos to achieve intelligent perception of indoor environments. However, widely deployed cameras are easily affected by lighting conditions in practical applications and are accompanied by serious privacy issues. Compared with cameras, indoor positioning services based on WiFi signals are not affected by various conditions and have a relatively small degree of privacy infringement. Therefore, indoor positioning systems based on WiFi signals have attracted the attention of a large number of researchers and have become a research hotspot in recent years. Summary of the invention

[0004] In view of this, the present application provides an object positioning method based on a wireless device, an object positioning apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

[0005] One aspect of the present application provides an object positioning method based on a wireless device, comprising:

[0006] In response to the indoor positioning instruction, a plurality of initial channel state information of the plurality of wireless devices is acquired, wherein the initial channel state information represents device data related to the target object collected by the wireless devices;

[0007] For each of the initial channel state information, performing deviation elimination processing on the initial channel state information based on a preset deviation elimination formula to obtain target channel state information;

[0008] Generate multiple data combination matrices according to the multiple target channel state information, wherein each of the data combination matrices includes multiple matrix row and column values;

[0009] For each of the data combination matrices, a target encoder is used to process a plurality of the matrix row and column values ​​and the position encoding data of the wireless device corresponding to each of the matrix row and column values ​​to generate a coordinate data set of the target object;

[0010] The weighted fusion processing is performed on the plurality of the above-mentioned coordinate data sets to obtain the target positioning information of the above-mentioned target object.

[0011] According to an embodiment of the present application, the initial channel state information is subjected to deviation elimination processing based on a preset deviation elimination formula to obtain target channel state information, including:

[0012] Eliminating the automatic power control deviation in the initial channel state information by using a scaling factor formula to generate a target scaling factor matrix;

[0013] The target channel state information is generated according to the initial channel state information and the target scaling factor matrix.

[0014] According to an embodiment of the present application, each subcarrier in the above initial channel state information As shown in formula (1), the above scaling factor formula is shown in formula (2):

[0015] (1)

[0016] in, It is the constant factor matrix that makes CSI amplitude scale in automatic power control, that is, automatic power control deviation, is a diagonal matrix representing the initial phase difference of the phase-locked loop, represents the channel state describing the physical world, represents the space mapping matrix, represents the steering matrix for potential beamforming, is the diagonal phase error matrix caused by imperfect hardware in the wireless device, including carrier frequency offset, sampling frequency offset, and symbol timing offset;

[0017] (2)

[0018] Among them, S is the scale factor matrix, that is, the target scaling factor matrix, r represents the received signal strength measured by the wireless device, is a matrix with all elements equal to 1, T stands for transpose, is the total number of subcarriers, Represents Hadamard division, that is, matrices are divided element by element.

[0019] According to an embodiment of the present application, generating the target channel state information according to the initial channel state information and the target scaling factor matrix includes:

[0020] Generate transition channel state information according to the initial channel state information and the target scaling factor matrix;

[0021] The target channel state information from which the guidance error and the diagonal phase error are eliminated is generated according to the transition channel state information and the conjugate transposed state information corresponding to the transition channel state information.

[0022] According to an embodiment of the present application, each subcarrier in the above transition channel state information As shown in formula (3), the target channel state information As shown in formula (4):

[0023] (3)

[0024] (4)

[0025] Among them, S is the target scaling factor matrix, is a diagonal matrix representing the initial phase difference of the phase-locked loop, represents the channel state describing the physical world, represents the space mapping matrix, represents the steering matrix used for potential beamforming, i.e., the steering error, is the diagonal phase error matrix caused by imperfect hardware in the wireless device, i.e., the diagonal phase error; That is, , H represents the conjugate transpose, column vector Depend on diagonal elements.

[0026] According to an embodiment of the present application, multiple data combination matrices are generated according to the multiple target channel state information, including:

[0027] Combining and dividing the plurality of target channel state information based on the received signal strength of each of the target channel state information to obtain a plurality of state information combinations;

[0028] Generate a channel state matrix corresponding to the target state information for the real part and the imaginary part of each target state information in each state information combination;

[0029] Generate a state combination vector of the state information combination according to the plurality of channel state matrices, wherein the state combination vector has a vector dimension;

[0030] The data combination matrix corresponding to the state information combination is generated according to the vector dimension and the number of the target state information in the state information combination.

[0031] According to an embodiment of the present application, a plurality of the target channel state information are combined and divided based on the received signal strength of each of the target channel state information to obtain a plurality of state information combinations, including:

[0032] Sorting the plurality of target channel state information based on the received signal strength to obtain a plurality of sorted target channel state information;

[0033] Selecting a preset number of the target channel state information from the sorted plurality of target channel state information;

[0034] A preset number of target status information are divided to obtain a plurality of the above status information combinations.

[0035] According to an embodiment of the present application, a target encoder is used to process a plurality of the matrix row and column values ​​and position encoding data of a wireless device corresponding to each of the matrix row and column values ​​to generate a coordinate data set of the target object, including:

[0036] For each of the above data combination matrices, a plurality of the above matrix row and column values ​​and a plurality of the above position coding data are subjected to data splicing processing to obtain an input data sequence;

[0037] Process the above input data sequence using a linear mapping layer to obtain a target mapping matrix;

[0038] Use the multi-head attention mechanism layer to process the above target mapping matrix to obtain the first attention feature;

[0039] Processing the plurality of first attention features corresponding to the plurality of data combination matrices and the plurality of target mapping matrices using a first normalization layer to obtain a first normalized feature;

[0040] The first normalized feature is processed by the feed-forward layer to obtain a matrix feature;

[0041] Using a second normalization layer to process the matrix features and the first normalized features, to obtain second normalized features;

[0042] The second normalized feature is processed by a multi-layer perceptron to obtain a coordinate data set corresponding to each of the data combination matrices.

[0043] According to an embodiment of the present application, the above-mentioned coordinate data set includes coordinate parameters and weights corresponding to the above-mentioned coordinate parameters.

[0044] According to an embodiment of the present application, weight fusion processing is performed on the plurality of coordinate data sets to obtain target positioning information of the target object, including:

[0045] The target positioning information is generated according to the plurality of coordinate parameters and the weight corresponding to each of the coordinate parameters.

[0046] Another aspect of the present application provides an object positioning apparatus based on a wireless device, comprising:

[0047] An acquisition module, configured to acquire, in response to an indoor positioning instruction, a plurality of initial channel state information of the plurality of wireless devices, wherein the initial channel state information represents device data related to a target object collected by the wireless devices;

[0048] A deviation elimination module, configured to perform deviation elimination processing on each of the initial channel state information based on a preset deviation elimination formula to obtain target channel state information;

[0049] A first generating module is used to generate a plurality of data combination matrices according to the plurality of target channel state information, wherein each of the data combination matrices includes a plurality of matrix row and column values;

[0050] A second generating module is used for processing, for each of the data combination matrices, a plurality of matrix row and column values ​​and position encoding data of the wireless device corresponding to each of the matrix row and column values ​​using a target encoder to generate a coordinate data set of the target object;

[0051] The module is used to perform weight fusion processing on the plurality of coordinate data sets to obtain the target positioning information of the target object.

[0052] Another aspect of the present application provides an electronic device, comprising:

[0053] one or more processors;

[0054] a memory for storing one or more programs,

[0055] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0056] Another aspect of the present application provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method described above when executed.

[0057] Another aspect of the present application provides a computer program product, which includes computer executable instructions, and the instructions are used to implement the method as described above when executed.

[0058] The target channel state information is obtained by performing deviation elimination processing on the initial channel state information based on a preset deviation elimination formula, thereby generating multiple data combination matrices based on the multiple target channel state information, and for each of the data combination matrices, using a target encoder to process multiple matrix row and column values ​​and the position encoding data of the wireless device corresponding to each matrix row and column value to generate a coordinate data set of the target object, and then performing weight fusion processing on the multiple coordinate data sets to obtain the target positioning information of the target object. Since the initial channel state information is subjected to deviation elimination processing based on the preset deviation elimination formula, the positioning accuracy of the target object can be improved, and the privacy and security of the user are effectively protected. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The above and other objects, features and advantages of the present application will become more apparent through the following description of the embodiments of the present application with reference to the accompanying drawings, in which:

[0060] Figure 1 An exemplary system architecture to which a wireless device-based object positioning method according to an embodiment of the present application can be applied is shown;

[0061] Figure 2 A flowchart of a method for positioning an object based on a wireless device according to an embodiment of the present application is shown;

[0062] Figure 3 A processing flow chart of a target encoder according to an embodiment of the present application is shown;

[0063] Figure 4 A schematic diagram of a usage scenario of an object positioning method according to an embodiment of the present application is shown;

[0064] Figure 5 A schematic diagram showing the difference in channel state information according to an embodiment of the present application is shown;

[0065] Figure 6 A schematic diagram showing the use of the object positioning method according to an embodiment of the present application is shown;

[0066] Figure 7 A schematic diagram showing comparison of positioning error results according to an embodiment of the present application is shown;

[0067] Figure 8 A schematic diagram showing a change in positioning effect according to an embodiment of the present application is shown;

[0068] Fig. 9 A block diagram of an object positioning device according to an embodiment of the present application is shown;

[0069] Fig.10A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0070] Below, embodiments of the present application will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present application. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present application. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present application.

[0071] The terms used herein are only for describing specific embodiments and are not intended to limit the present application. The terms "include", "comprising", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0072] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0073] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0074] Indoor positioning is essential for various applications such as navigation, asset tracking, and improved user experience in smart environments. To achieve accurate indoor positioning, a variety of technologies have been adopted, including RFID, Bluetooth, UWB (ultra-wideband), and WiFi. Among them, WiFi-based positioning stands out because it can reuse existing infrastructure, making the related solutions highly scalable. Compared with RSSI (received signal strength indication), CSI (channel state information) can provide more fine-grained information due to OFDM (orthogonal frequency division multiplexing) modulation technology, and has attracted widespread attention in WiFi indoor positioning. After a lot of efforts, CSI-based methods are believed to be able to achieve decimeter-level positioning accuracy in various complex scenarios. Among all related studies, deep learning-based methods are better able to cope with complex indoor environments due to their powerful nonlinear fitting capabilities, and have achieved impressive performance through various deep learning techniques.

[0075] However, existing research mainly relies on dedicated hardware and probe packets injected in laboratory environments. In actual ISAC (Integrated Sensing and Communication) systems, there are multiple problems that hinder the practical application of these methods. In order to advance positioning research in real scenarios, we mainly consider improvements from three aspects:

[0076] 1. Biased CSI: Due to the communication requirements between deployed commercial APs (access points) and off-the-shelf terminals, the CSI measured on the AP side will contain various deviations that vary over time, which means that the CSI cannot be directly mapped to the exact location. If these deviations that vary over time are not eliminated, the positioning performance will be significantly degraded.

[0077] 2. Limited hardware: For commercial APs deployed in the wild, the antenna layout is usually uneven (usually not half-wavelength spacing) to maintain communication performance, and the number of antennas is limited due to hardware cost constraints. In addition, in actual scenarios, since terminals and APs usually need to perform high-speed data transmission in a relatively stable environment, which is not common, it is difficult to reliably obtain CSI with large bandwidths (such as 80 MHz, 160 MHz). These problems combine to reduce the quality of CSI measured by the AP, resulting in degraded positioning performance.

[0078] 3. Heterogeneity of terminals: For various off-the-shelf terminals on the market, they usually use WiFi chips from different manufacturers. This will introduce additional deviations to the CSI measured by the AP and cause different distributions of CSI data corresponding to different terminals. Faced with such heterogeneous CSI, it is difficult to apply a single machine learning model for positioning.

[0079] In view of this, an embodiment of the present application provides an object positioning method and an object positioning device based on a wireless device, the method comprising: obtaining multiple initial channel state information of multiple wireless devices in response to an indoor positioning instruction, wherein the initial channel state information represents device data related to a target object collected by the wireless device; for each initial channel state information, performing deviation elimination processing on the initial channel state information based on a preset deviation elimination formula to obtain target channel state information; generating multiple data combination matrices based on the multiple target channel state information, wherein each data combination matrix includes multiple matrix row and column values; for each data combination matrix, using a target encoder to process multiple matrix row and column values ​​and position encoding data of the wireless device corresponding to each matrix row and column value to generate a coordinate data set of the target object; performing weight fusion processing on the multiple coordinate data sets to obtain target positioning information of the target object.

[0080] In the embodiments of this application, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information and network security.

[0081] In the embodiments of the present application, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0082] Figure 1 An exemplary system architecture 100 to which a wireless device-based object positioning method according to an embodiment of the present application can be applied is shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present application can be applied, in order to help those skilled in the art understand the technical content of the present application, but it does not mean that the embodiments of the present application cannot be used in other devices, systems, environments or scenarios.

[0083] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0084] The user may use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only for example).

[0085] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0086] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0087] It should be noted that the object positioning method based on a wireless device provided in the embodiment of the present application can generally be executed by the server 105. Accordingly, the object positioning device provided in the embodiment of the present application can generally be set in the server 105. The object positioning method based on a wireless device provided in the embodiment of the present application can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Correspondingly, the object positioning device provided in the embodiment of the present application can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0088] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only . According to the implementation requirements, there can be any number of terminal devices, networks and servers.

[0089] Figure 2 A flow chart of an object positioning method based on a wireless device according to an embodiment of the present application is shown.

[0090] like Figure 2 As shown, the object positioning method based on a wireless device includes operations S201 to S205.

[0091] In operation S201, in response to an indoor positioning instruction, multiple initial channel state information of multiple wireless devices is acquired, wherein the initial channel state information represents device data related to a target object collected by the wireless device;

[0092] In operation S202, for each initial channel state information, deviation elimination processing is performed on the initial channel state information based on a preset deviation elimination formula to obtain target channel state information;

[0093] In operation S203, a plurality of data combination matrices are generated according to the plurality of target channel state information, wherein each data combination matrix includes a plurality of matrix row and column values;

[0094] In operation S204, for each data combination matrix, a target encoder is used to process a plurality of matrix row and column values ​​and position encoding data of the wireless device corresponding to each matrix row and column value to generate a coordinate data set of the target object;

[0095] In operation S205, weight fusion processing is performed on the multiple coordinate data sets to obtain target positioning information of the target object.

[0096] According to the embodiments of the present application, the wireless device may be any type of WiFi device AP. The initial channel state information may be the channel state information (CSI) generated by the wireless device AP. The indoor positioning instruction may be generated by the electronic device in response to the operation input by the staff on the mobile phone, computer and other electronic devices, or the instruction may be automatically generated by the electronic device. The target object may be any user, robot, pet, etc.

[0097] According to an embodiment of the present application, since there are various deviations that vary with time in the initial channel state information transmitted by the wireless device, after the initial channel state information is acquired, the initial channel state information is subjected to deviation elimination processing based on a preset deviation elimination formula, thereby obtaining the target channel state information after the deviation is eliminated.

[0098] According to an embodiment of the present application, after obtaining a plurality of target channel state information, a plurality of data combination matrices may be generated according to the plurality of target channel state information, wherein each data combination matrix includes a plurality of matrix row and column values.

[0099] According to an embodiment of the present application, multiple matrix row and column values ​​and the position encoding data of the wireless device corresponding to each matrix row and column value are simultaneously input into the target encoder to process them in parallel, thereby obtaining multiple coordinate data sets about the target object, and then the multiple coordinate data sets are fused based on the weight of each coordinate data set to obtain the target positioning information of the target object. The target encoder can be a Transformer encoder.

[0100] According to an embodiment of the present application, the target channel state information is obtained by performing deviation elimination processing on the initial channel state information based on a preset deviation elimination formula, thereby generating multiple data combination matrices based on multiple target channel state information, and for each data combination matrix, using a target encoder to process multiple matrix row and column values ​​and the position encoding data of the wireless device corresponding to each matrix row and column value to generate a coordinate data set of the target object, and then performing weight fusion processing on the multiple coordinate data sets to obtain the target positioning information of the target object. Since the initial channel state information is subjected to deviation elimination processing based on the preset deviation elimination formula, the positioning accuracy of the target object can be improved, and the privacy and security of the user are effectively protected.

[0101] According to an embodiment of the present application, the initial channel state information is subjected to deviation elimination processing based on a preset deviation elimination formula to obtain target channel state information, including:

[0102] Eliminate the automatic power control deviation in the initial channel state information using the scaling factor formula to generate a target scaling factor matrix;

[0103] Target channel state information is generated according to the initial channel state information and the target scaling factor matrix.

[0104] According to the embodiment of the present application, during actual positioning, the chip of each wireless device AP will collect initial channel state information CSI based on data traffic. For the initial channel state information CSI collected by each wireless device AP, each subcarrier in the initial channel state information CSI The signal can be expressed by formula (1).

[0105] (1)

[0106] in, It is the constant factor matrix that makes CSI amplitude scale in automatic power control, that is, automatic power control deviation, is a diagonal matrix representing the initial phase difference of the phase-locked loop, represents the channel state describing the physical world, represents the space mapping matrix, represents the steering matrix for potential beamforming, is a diagonal phase error matrix caused by imperfect hardware in wireless devices, including carrier frequency offset CFO, sampling frequency offset SFO and symbol timing offset STO.

[0107] According to an embodiment of the present application, in formula (1), even if the position of the target object does not change, , , It will also change over time and is a deviation term that needs to be eliminated.

[0108] According to an embodiment of the present application, the automatic power control deviation in the initial channel state information is calculated using the scaling factor formula shown in formula (2). Eliminate and generate the target scaling factor matrix S.

[0109] (2)

[0110] Among them, S is the scale factor matrix, that is, the target scaling factor matrix, r represents the received signal strength measured by the wireless device, is a matrix with all elements equal to 1, T stands for transpose, is the total number of subcarriers, Represents Hadamard division, that is, matrices are divided element by element.

[0111] According to an embodiment of the present application, generating target channel state information according to initial channel state information and a target scaling factor matrix includes:

[0112] generating transition channel state information according to the initial channel state information and the target scaling factor matrix;

[0113] Target channel state information from which a guidance error and a diagonal phase error are eliminated is generated according to the transitional channel state information and the conjugate transposed state information corresponding to the transitional channel state information.

[0114] According to an embodiment of the present application, based on the initial channel state information and the target scaling factor matrix S, each subcarrier in the transition channel state information as shown in formula (3) is generated. .

[0115] (3)

[0116] According to an embodiment of the present application, according to each subcarrier in the transition channel state information and the conjugate transposed state information corresponding to the transition channel state information , generating the target channel state information as shown in formula (4) .

[0117] (4)

[0118] Among them, S is the target scaling factor matrix, is a diagonal matrix representing the initial phase difference of the phase-locked loop, represents the channel state describing the physical world, represents the space mapping matrix, represents the steering matrix used for potential beamforming, i.e., the steering error, is the diagonal phase error matrix caused by imperfect hardware in the wireless device, i.e., the diagonal phase error; That is, , H represents the conjugate transpose, column vector Depend on The diagonal elements of . In formula (4), , To be eliminated.

[0119] According to an embodiment of the present application, multiple data combination matrices are generated according to multiple target channel state information, including:

[0120] Combining and dividing the multiple target channel state information based on the received signal strength of each target channel state information to obtain multiple state information combinations;

[0121] Generate a channel state matrix corresponding to the target state information for the real part and the imaginary part of each target state information in each state information combination;

[0122] Generate a state combination vector of state information combination according to a plurality of channel state matrices, wherein the state combination vector has a vector dimension;

[0123] According to the vector dimension and the amount of target state information in the state information combination, a data combination matrix corresponding to the state information combination is generated.

[0124] Table 1 The process of generating data combination matrix

[0125]

[0126] According to the embodiment of the present application, see Table 1, the data combination matrix It can be expressed by formula (5):

[0127] , (5)

[0128] Wherein, J represents the number of state information combinations, K represents the number of wireless devices AP in the state information combination, and D represents the vector dimension.

[0129] According to an embodiment of the present application, M in Table 1 is the number of wireless devices, is the initial channel state information.

[0130] According to an embodiment of the present application, multiple target channel state information are combined and divided based on the received signal strength of each target channel state information to obtain multiple state information combinations, including:

[0131] Sorting multiple target channel state information based on received signal strength RSSI to obtain sorted multiple target channel state information;

[0132] Selecting a preset number of target state information from the sorted plurality of target channel state information;

[0133] A preset number of target status information are divided to obtain multiple status information combinations.

[0134] According to an embodiment of the present application, the preset number S may be any positive integer, for example, 5. See Table 1 for a specific process of generating a state information combination.

[0135] Figure 3 A processing flow chart of a target encoder according to an embodiment of the present application is shown.

[0136] According to the embodiments of the present application, unbiased data corresponding to different locations can be obtained according to the data processing steps outlined above. However, there are various types of wireless device terminals on the market, produced by different manufacturers and equipped with different WiFi chips. Due to the differences in terminal hardware, There will be different implementations, resulting in different distributions of data from different terminals. In order to process data with different data distributions, the present application designs a target encoder based on a Transformer encoder to process data distributions of different terminals.

[0137] According to an embodiment of the present application, a target encoder is used to process a plurality of matrix row and column values ​​and position encoding data of a wireless device corresponding to each matrix row and column value to generate a coordinate data set of a target object, including:

[0138] For each data combination matrix, multiple matrix row and column values ​​and multiple position encoding data are processed by data concatenation to obtain an input data sequence;

[0139] Use the linear projection layer to process the input data sequence to obtain the target mapping matrix;

[0140] Use the multi-head attention mechanism layer Multi-Head Attention to process the target mapping matrix and obtain the first attention feature;

[0141] Using the first normalization layer Add&Norm to process the multiple first attention features corresponding to the multiple data combination matrices and the multiple target mapping matrices to obtain the first normalized features;

[0142] The first normalized feature is processed by the feed forward layer to obtain the matrix feature;

[0143] The second normalization layer Add&Norm is used to process the matrix features and the first normalized features to obtain the second normalized features;

[0144] The second normalized feature is processed by a multilayer perceptron to obtain a coordinate data set corresponding to each data combination matrix.

[0145] According to the embodiments of the present application, see Figure 3 .Will and Perform data splicing processing to obtain the input data sequence. Then input it into the target encoder for processing to obtain the coordinate data set ( ).

[0146] According to an embodiment of the present application, the coordinate data set includes coordinate parameters and weights corresponding to the coordinate parameters.

[0147] According to an embodiment of the present application, weight fusion processing is performed on multiple coordinate data sets to obtain target positioning information of the target object, including:

[0148] Target positioning information is generated according to a plurality of coordinate parameters and a weight corresponding to each coordinate parameter.

[0149] According to the embodiment of the present application, the observation fusion layer is used to obtain the coordinates of the and the weights corresponding to each coordinate parameter , generate target positioning information .

[0150] Figure 4 A schematic diagram of a usage scenario of an object positioning method according to an embodiment of the present application is shown. Figure 5 A schematic diagram showing the differences in channel state information according to an embodiment of the present application is shown. Figure 6 A schematic diagram of the use of the object positioning method according to an embodiment of the present application is shown. Figure 7 A schematic diagram showing comparison of positioning error results according to an embodiment of the present application is shown. Figure 8 A schematic diagram showing changes in positioning effects according to an embodiment of the present application is shown.

[0151] According to the embodiment of this application, an actual mobile phone terminal is used as the positioning target, and multiple deployed commercial APs are used as data collection terminals. The receiving APs are equipped with two antennas, and the carrier frequency of the WiFi signal is 5GHz. The APs existing in the detection space are manually marked by the experimenter. The scene of this experiment is as follows Figure 4 As shown in the figure, the experimental scene is the second floor of Building 1 on campus. The true value of the data is collected through an ultra-wideband system.

[0152] According to the embodiments of the present application, Figure 5 In the indoor scene in (a), the CSI obtained by processing data using the wireless device and the algorithm of the present application is as follows: Figure 5 As shown in (b), the difference is quite large, where the triangle is the initial channel state information collected by the wireless device, and the circle is the target channel state information of this application.

[0153] According to the embodiment of the present application, the algorithm flow chart of the whole system is as follows: Figure 6 As shown; first, multiple APs measure the CSI signal (i.e., initial channel state information) from the data traffic generated by their communication with the mobile phone. After measuring the CSI signal, each AP sends the data to the data server for storage. Secondly, when positioning, it is necessary to eliminate the deviation in the CSI data in accordance with the object positioning method of the present application. In order to construct data for high-precision positioning, it is necessary to obtain a data combination matrix based on the algorithm of the present application. Finally, by using the obtained data combination matrix to train the encoder, a target encoder for positioning can be obtained.

[0154] According to the embodiment of the present application, after training, the entire system can achieve a median positioning error at the decimeter level in a 65m*82m room. The positioning error result comparison chart is as follows: Figure 7 As shown in the figure. The algorithm proposed in the patent is represented by Proposed. It can be seen that the performance of the algorithm proposed in the patent is much better than other well-known algorithms in the field. This is because we analyze the actual data, eliminate the time-varying data deviation, construct input data for high-precision positioning through the data organization algorithm, and build a network based on the Transformer Encoder to process the data distribution of different mobile phones. Figure 7 The activity area (Lounge) in (a) Figure 7 The corridor in (b).

[0155] According to an embodiment of the present application, Figure 8 (a) and Figure 8(b) shows the results of the positioning effect in the rest area and corridor as the number of APs changes. It can be seen that as the number of APs gradually increases, the positioning accuracy also shows an increasing trend. This is because the more APs there are, the more deterministic the input data constructed by the input algorithm can represent different locations.

[0156] Fig. 9 A block diagram of an object positioning device according to an embodiment of the present application is shown.

[0157] like Fig. 9 As shown, the object positioning apparatus 1000 based on a wireless device includes an acquisition module 1010 , a deviation elimination module 1020 , a first generation module 1030 , a second generation module 1040 , and a obtaining module 1050 .

[0158] The acquisition module 1010 is used to acquire multiple initial channel state information of multiple wireless devices in response to the indoor positioning instruction, wherein the initial channel state information represents device data related to the target object collected by the wireless device;

[0159] The deviation elimination module 1020 is used to perform deviation elimination processing on each initial channel state information based on a preset deviation elimination formula to obtain target channel state information;

[0160] A first generating module 1030 is used to generate a plurality of data combination matrices according to a plurality of target channel state information, wherein each data combination matrix includes a plurality of matrix row and column values;

[0161] The second generating module 1040 is used to process a plurality of matrix row and column values ​​and the position encoding data of the wireless device corresponding to each matrix row and column value by using a target encoder for each data combination matrix, so as to generate a coordinate data set of the target object;

[0162] The obtaining module 1050 is used to perform weight fusion processing on multiple coordinate data sets to obtain target positioning information of the target object.

[0163] According to an embodiment of the present application, the target channel state information is obtained by performing deviation elimination processing on the initial channel state information based on a preset deviation elimination formula, thereby generating multiple data combination matrices based on multiple target channel state information, and for each data combination matrix, using a target encoder to process multiple matrix row and column values ​​and the position encoding data of the wireless device corresponding to each matrix row and column value to generate a coordinate data set of the target object, and then performing weight fusion processing on the multiple coordinate data sets to obtain the target positioning information of the target object. Since the initial channel state information is subjected to deviation elimination processing based on the preset deviation elimination formula, the positioning accuracy of the target object can be improved, and the privacy and security of the user are effectively protected.

[0164] According to an embodiment of the present application, the deviation elimination module 1020 includes:

[0165] An elimination unit, used to eliminate the automatic power control deviation in the initial channel state information by using a scaling factor formula to generate a target scaling factor matrix;

[0166] The first generating unit is used to generate target channel state information according to the initial channel state information and the target scaling factor matrix.

[0167] According to an embodiment of the present application, the first generating unit includes:

[0168] A first generating subunit, configured to generate transition channel state information according to initial channel state information and a target scaling factor matrix;

[0169] The second generating subunit is used to generate target channel state information with the guided error and the diagonal phase error eliminated according to the transition channel state information and the conjugate transposed state information corresponding to the transition channel state information.

[0170] According to an embodiment of the present application, the first generating module 1030 includes:

[0171] An obtaining unit, configured to combine and divide a plurality of target channel state information based on a received signal strength of each target channel state information to obtain a plurality of state information combinations;

[0172] A second generating unit is used to generate a channel state matrix corresponding to the target state information according to the real part and the imaginary part of each target state information in each state information combination;

[0173] A third generating unit is used to generate a state combination vector of the state information combination according to the multiple channel state matrices, wherein the state combination vector has a vector dimension;

[0174] The fourth generating unit is used to generate a data combination matrix corresponding to the state information combination according to the vector dimension and the amount of target state information in the state information combination.

[0175] According to an embodiment of the present application, the obtaining unit includes:

[0176] A sorting subunit, used to sort the multiple target channel state information based on the received signal strength to obtain sorted multiple target channel state information;

[0177] A selection subunit, used to select a preset number of target state information from the sorted plurality of target channel state information;

[0178] The division subunit is used to divide a preset number of target state information to obtain multiple state information combinations.

[0179] According to an embodiment of the present application, the second generation module 1040 includes:

[0180] A splicing unit is used for performing data splicing processing on a plurality of matrix row and column values ​​and a plurality of position coding data for each data combination matrix to obtain an input data sequence;

[0181] A mapping unit, used for processing an input data sequence using a linear mapping layer to obtain a target mapping matrix;

[0182] The attention unit is used to process the target mapping matrix using the multi-head attention mechanism layer to obtain the first attention feature;

[0183] A first normalization unit, used for processing a plurality of first attention features corresponding to a plurality of data combination matrices and a plurality of target mapping matrices using a first normalization layer to obtain a first normalized feature;

[0184] A feed-forward unit, used for processing the first normalized feature using the feed-forward layer to obtain a matrix feature;

[0185] A second normalization unit, used for processing the matrix features and the first normalized features by using a second normalization layer to obtain second normalized features;

[0186] The multi-layer perception unit is used to process the second normalized feature using a multi-layer perceptron to obtain a coordinate data set corresponding to each data combination matrix.

[0187] According to an embodiment of the present application, the coordinate data set includes coordinate parameters and weights corresponding to the coordinate parameters.

[0188] According to an embodiment of the present application, the obtaining module 1050 includes:

[0189] The fusion unit is used to generate target positioning information according to multiple coordinate parameters and a weight corresponding to each coordinate parameter.

[0190] According to the embodiments of the present application, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present application, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present application, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present application, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be executed.

[0191] For example, any multiple of the acquisition module 1010, the deviation elimination module 1020, the first generation module 1030, the second generation module 1040, and the acquisition module 1050 can be combined in one module / unit / sub-unit for implementation, or any one of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to an embodiment of the present application, at least one of the acquisition module 1010, the deviation elimination module 1020, the first generation module 1030, the second generation module 1040, and the acquisition module 1050 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, at least one of the acquisition module 1010, the deviation elimination module 1020, the first generation module 1030, the second generation module 1040, and the acquisition module 1050 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0192] It should be noted that the object positioning device part in the embodiment of the present application corresponds to the object positioning method part in the embodiment of the present application. The description of the object positioning device part specifically refers to the object positioning method part, which will not be repeated here.

[0193] Fig.10 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present application is shown. Fig.10 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0194] like Fig.10 As shown, the electronic device 1100 according to an embodiment of the present application includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage part 1108 to a random access memory (RAM) 1103. The processor 1101 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1101 may also include an onboard memory for caching purposes. The processor 1101 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present application.

[0195] In RAM 1103, various programs and data required for the operation of electronic device 1100 are stored. Processor 1101, ROM 1102 and RAM 1103 are connected to each other via bus 1104. Processor 1101 performs various operations of the method flow according to the embodiment of the present application by executing the program in ROM 1102 and / or RAM 1103. It should be noted that the program can also be stored in one or more memories other than ROM 1102 and RAM 1103. Processor 1101 can also perform various operations of the method flow according to the embodiment of the present application by executing the program stored in the one or more memories.

[0196] According to an embodiment of the present application, the electronic device 1100 may further include an input / output (I / O) interface 1105, which is also connected to the bus 1104. The electronic device 1100 may further include one or more of the following components connected to the input / output (I / O) interface 1105: an input portion 1106 including a keyboard, a mouse, etc.; an output portion 1107 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 1108 including a hard disk, etc.; and a communication portion 1109 including a network interface card such as a LAN card, a modem, etc. The communication portion 1109 performs communication processing via a network such as the Internet. The drive 1110 is also connected to the input / output (I / O) interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed, so that the computer program read therefrom is installed into the storage portion 1108 as needed.

[0197] According to an embodiment of the present application, the method flow according to the embodiment of the present application can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1109, and / or installed from the removable medium 1111. When the computer program is executed by the processor 1101, the above-mentioned functions defined in the system of the embodiment of the present application are executed. According to an embodiment of the present application, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0198] The present application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present application is implemented.

[0199] According to an embodiment of the present application, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0200] For example, according to an embodiment of the present application, the computer-readable storage medium may include the ROM 1102 and / or the RAM 1103 described above and / or one or more memories other than the ROM 1102 and the RAM 1103 .

[0201] An embodiment of the present application also includes a computer program product, which includes a computer program, which contains program code for executing the method provided by the embodiment of the present application. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the method provided by the embodiment of the present application.

[0202] When the computer program is executed by the processor 1101, the above functions defined in the system / device of the embodiment of the present application are executed. According to the embodiment of the present application, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0203] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 1109, and / or installed from a removable medium 1111. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0204] According to an embodiment of the present application, the program code for executing the computer program provided by the embodiment of the present application can be written in any combination of one or more programming languages, and specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, such as Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or completely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0205] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of the boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It will be appreciated by those skilled in the art that the features recorded in the various embodiments of the present application can be combined and / or combined in a variety of ways, even if such a combination or combination is not clearly recorded in the present application. In particular, without departing from the spirit and teachings of the present application, the features described in the various embodiments of the present application may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present application.

[0206] The embodiments of the present application are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present application. Although each embodiment is described above, this does not mean that the measures in each embodiment cannot be used in combination advantageously. Without departing from the scope of the present application, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present application.

Claims

1. An object positioning method based on a wireless device, characterized in that: include: In response to the indoor positioning instruction, obtaining a plurality of initial channel state information of the plurality of wireless devices, wherein the initial channel state information represents device data related to the target object collected by the wireless device; Eliminating the automatic power control deviation in the initial channel state information by using a scaling factor formula to generate a target scaling factor matrix; generating target channel state information according to the initial channel state information and the target scaling factor matrix; Generate a plurality of data combination matrices according to the plurality of target channel state information, wherein each of the data combination matrices includes a plurality of matrix row and column values; For each of the data combination matrices, using a target encoder to process a plurality of the matrix row and column values ​​and the position encoding data of the wireless device corresponding to each of the matrix row and column values, to generate a coordinate data set of the target object; Performing weight fusion processing on the plurality of coordinate data sets to obtain target positioning information of the target object; Among them, each subcarrier in the initial channel state information As shown in formula (1), the scaling factor formula is shown in formula (2), （1） in, It is the constant factor matrix that makes CSI amplitude scale in automatic power control, that is, automatic power control deviation, is a diagonal matrix representing the initial phase difference of the phase-locked loop, represents the channel state describing the physical world, represents the space mapping matrix, represents the steering matrix for potential beamforming, is the diagonal phase error matrix caused by imperfect hardware in the wireless device, including carrier frequency offset, sampling frequency offset, and symbol timing offset; （2） Among them, S is the scale factor matrix, that is, the target scaling factor matrix, r represents the received signal strength measured by the wireless device, is a matrix with all elements equal to 1, T stands for transpose, is the total number of subcarriers, Represents Hadamard division, that is, matrices are divided element by element.

2. The method according to claim 1, characterized in that Generating the target channel state information according to the initial channel state information and the target scaling factor matrix includes: generating transition channel state information according to the initial channel state information and the target scaling factor matrix; The target channel state information from which the guidance error and the diagonal phase error are eliminated is generated according to the transitional channel state information and the conjugate transposed state information corresponding to the transitional channel state information.

3. The method according to claim 2, characterized in that Each subcarrier in the transition channel state information As shown in formula (3), the target channel state information As shown in formula (4): （3） （4） Among them, S is the target scaling factor matrix, is a diagonal matrix representing the initial phase difference of the phase-locked loop, represents the channel state describing the physical world, represents the space mapping matrix, represents the steering matrix used for potential beamforming, i.e., the steering error, is the diagonal phase error matrix caused by imperfect hardware in the wireless device, i.e., the diagonal phase error; That is, , H represents the conjugate transpose, column vector Depend on diagonal elements.

4. The method according to claim 1, characterized in that: Generating a plurality of data combination matrices according to the plurality of target channel state information, including: Combining and dividing the plurality of target channel state information based on the received signal strength of each of the target channel state information to obtain a plurality of state information combinations; Generate a channel state matrix corresponding to the target state information for the real part and the imaginary part of each target state information in each state information combination; Generate a state combination vector of the state information combination according to the plurality of channel state matrices, wherein the state combination vector has a vector dimension; The data combination matrix corresponding to the state information combination is generated according to the vector dimension and the quantity of the target state information in the state information combination.

5. The method according to claim 4, characterized in that Combining and dividing the plurality of target channel state information based on the received signal strength of each of the target channel state information to obtain a plurality of state information combinations, including: Sorting the plurality of target channel state information based on the received signal strength to obtain a plurality of sorted target channel state information; Selecting a preset number of target state information from the sorted plurality of target channel state information; A preset number of target status information are divided to obtain a plurality of status information combinations.

6. The method according to claim 1, characterized in that Processing a plurality of the matrix row and column values ​​and the position encoding data of the wireless device corresponding to each of the matrix row and column values ​​by using a target encoder to generate a coordinate data set of the target object, comprising: For each of the data combination matrices, a plurality of matrix row and column values ​​and a plurality of the position coding data are subjected to data splicing processing to obtain an input data sequence; Processing the input data sequence using a linear mapping layer to obtain a target mapping matrix; Processing the target mapping matrix using a multi-head attention mechanism layer to obtain a first attention feature; Processing the plurality of first attention features corresponding to the plurality of data combination matrices and the plurality of target mapping matrices using a first normalization layer to obtain a first normalized feature; Processing the first normalized features using a feed-forward layer to obtain matrix features; Processing the matrix features and the first normalized features using a second normalization layer to obtain second normalized features; The second normalized features are processed using a multilayer perceptron to obtain a coordinate data set corresponding to each of the data combination matrices.

7. The method according to claim 1 or 6, characterized in that: The coordinate data set includes coordinate parameters and weights corresponding to the coordinate parameters; The weight fusion process is performed on the plurality of coordinate data sets to obtain the target positioning information of the target object, including: The target positioning information is generated according to the plurality of coordinate parameters and a weight corresponding to each of the coordinate parameters.

8. An object positioning device based on a wireless device, characterized in that: include: An acquisition module, configured to acquire, in response to an indoor positioning instruction, a plurality of initial channel state information of a plurality of the wireless devices, wherein the initial channel state information represents device data related to a target object collected by the wireless device; Deviation elimination module, including: an elimination unit, configured to eliminate the automatic power control deviation in the initial channel state information by using a scaling factor formula to generate a target scaling factor matrix, wherein the target scaling factor matrix is ​​constructed according to the received signal strength measured by the wireless device, the initial channel state information, and the number of subcarriers in the initial channel state information; A first generating unit, configured to generate target channel state information according to the initial channel state information and the target scaling factor matrix; A first generating module, configured to generate a plurality of data combination matrices according to the plurality of target channel state information, wherein each of the data combination matrices includes a plurality of matrix row and column values; A second generating module is used for processing, for each of the data combination matrices, a plurality of matrix row and column values ​​and position encoding data of the wireless device corresponding to each of the matrix row and column values ​​using a target encoder to generate a coordinate data set of the target object; An obtaining module is used to perform weight fusion processing on the plurality of coordinate data sets to obtain target positioning information of the target object; Among them, each subcarrier in the initial channel state information As shown in formula (1), the scaling factor formula is shown in formula (2), （1） in, It is the constant factor matrix that makes CSI amplitude scale in automatic power control, that is, automatic power control deviation, is a diagonal matrix representing the initial phase difference of the phase-locked loop, represents the channel state describing the physical world, represents the space mapping matrix, represents the steering matrix for potential beamforming, is the diagonal phase error matrix caused by imperfect hardware in the wireless device, including carrier frequency offset, sampling frequency offset, and symbol timing offset; （2） Among them, S is the scale factor matrix, that is, the target scaling factor matrix, r represents the received signal strength measured by the wireless device, is a matrix with all elements equal to 1, T stands for transpose, is the total number of subcarriers, Represents Hadamard division, that is, matrices are divided element by element.

Images