High-precision positioning method and system

Abstract

The invention discloses a high-precision positioning method and system, and the method comprises the steps: carrying out the signal interaction with a base station through a multi-antenna array, and obtaining a transmitting signal and a receiving signal; calculating an initial direction of the target terminal device and the base station according to the transmitting signal or the receiving signal, and correcting the initial signal direction by using a direction enhancement model to obtain final direction information of the target terminal device and the base station; acquiring propagation time of the transmitting signal and the receiving signal to calculate initial distance information between the target terminal equipment and the base station, and correcting the initial distance information by using a distance correction model to obtain corrected final distance information between the target terminal equipment and the base station; and calculating initial position information of the target terminal equipment according to the final direction information and the final distance information of the target terminal equipment and the base station, and correcting the initial position information of the target terminal equipment by using the received position information of the terminal equipment calculated by other terminal equipment to obtain final positioning information.

Description

Technical Field

[0001] The present application relates to the field of positioning technology, and in particular to a high-precision positioning method and system. Background Art

[0002] Direction and distance measurement (positioning) of mobile communication terminals is one of the most important technical reconnaissance methods in the public security industry. Before the widespread application of 5G mobile communication technology, existing technologies mainly relied on GPS, Location-Based Broadcasting (LBS) positioning technology, and 4G terminal direction and distance measurement. However, these technologies have the following problems:

[0003] 1. LBS positioning technology has insufficient positioning accuracy:

[0004] The positioning accuracy of LBS (cellular network) is usually in the range of tens to hundreds of meters, which is difficult to meet the needs of high-precision scenarios.

[0005] 2. GPS is not adaptable to the environment:

[0006] In complex environments such as indoors, tunnels, and underground parking lots, GPS signals are easily blocked and cannot provide reliable positioning services.

[0007] 3. 4G terminals have limited direction and ranging capabilities:

[0008] Existing terminals can usually only roughly estimate the direction through signal strength (RSSI) and cannot achieve accurate direction finding. Summary of the Invention

[0009] Based on this, in response to the above technical problems, a high-precision positioning method is provided to solve the problem that the existing technology cannot accurately locate.

[0010] In a first aspect, a high-precision positioning method is provided, the method comprising:

[0011] Using a base station positioning terminal multi-antenna array to perform signal interaction with a target terminal device to be located, obtaining signals transmitted by the base station positioning terminal to the target terminal device to be located and signals received by the base station positioning terminal from the target terminal device to be located;

[0012] Calculating a phase difference based on a transmitted signal or a received signal when the multi-antenna array interacts with the target terminal device to be located, extracting features of the received signal or the transmitted signal, and calculating a first direction of the target terminal to be located based on a pre-built deep learning-based direction enhancement model; the features of the received signal or the transmitted signal include signal strength and frequency offset; estimating a second direction of the target terminal to be located using an attenuation model and the signal strength of the current received signal or the transmitted signal, and performing a weighted sum of the first and second directions of the target terminal to be located to obtain a final direction;

[0013] Obtaining the propagation time of the received signal or transmitted signal of each antenna according to the transmitted signal or received signal when the multi-antenna array interacts with the target terminal device to be located, so as to calculate the initial ranging result with the target terminal to be located, and extracting the features of the received signal and the transmitted signal, and using the initial ranging result and the features of the received signal and the transmitted signal to correct the initial ranging result based on a pre-built deep learning-based distance correction model to obtain a first ranging result; using the attenuation model and the signal strength of the current received signal or transmitted signal to estimate the second distance of the target terminal to be located, and performing a weighted sum of the first ranging result and the second ranging result of the target terminal to be located to obtain a final distance;

[0014] The initial position information of the target terminal device is calculated based on the final direction and final distance of the target terminal to be located; and the initial position information of the target terminal device calculated by multiple base station positioning terminals is corrected to obtain the final positioning information.

[0015] In the above solution, optionally, the deep learning-based direction enhancement model is constructed by the following method:

[0016] Obtain the historical transmission or reception signals of the positioning terminal device interacting with the multi-array antenna, and obtain the actual signal direction of the positioning terminal device obtained through high-precision equipment calibration;

[0017] Extracting characteristics of a transmitted signal or a received signal interacting with a historical positioning terminal device, wherein the signal characteristics include: signal strength and frequency offset;

[0018] Calculate and extract the phase difference of the transmitted signal or received signal interacting with the historical positioning terminal device;

[0019] The phase difference between the transmitted signal and the received signal interacting with the historical positioning terminal device, the signal characteristics and the corresponding real signal direction are input into the convolutional neural network for training to obtain a direction enhancement model based on deep learning.

[0020] In the above scheme, optionally, the use of a multi-antenna array to interact with the target terminal device to be located also includes: using multi-band signal processing technology to use multiple frequency bands to interact with the target terminal device to be located to obtain transmission signals and reception signals in different frequency bands.

[0021] In the above solution, optionally, the attenuation model is constructed by the following formula:

[0022] P r (d) = P t +G t +Gr -20log 10 (d)-L f

[0023] Among them, P r (d) is the received power, P t is the transmission power, G t is the transmitting antenna gain, G r is the receiving antenna gain, d is the distance between the transmitter and the receiver, 20log 10 (d) is the free space path loss, L f For additional loss.

[0024] In the above solution, optionally, when using the multi-antenna array to perform signal interaction with the target terminal device to be located, a distributed time synchronization technology is used to ensure time consistency between the multiple multi-antenna arrays.

[0025] In the above solution, optionally, the initial location information of the target terminal device calculated by combining multiple base station positioning terminals is corrected to obtain the final positioning information, which includes:

[0026] The final location information of the target terminal is calculated using the following formula:

[0027]

[0028] Among them, (x, y) is the terminal device position to be solved, (x i ,y i ) is the position of the i-th terminal, d i It is the distance between the terminal and the terminal device.

[0029] In the above solution, optionally, the pre-built deep learning-based distance correction model is constructed by the following method:

[0030] Obtain the historical transmission or reception signals of the interaction between the positioning terminal device and the multi-array antenna, and obtain the actual distance value of the positioning terminal device obtained through high-precision equipment calibration;

[0031] Extracting characteristics of a transmitted signal or a received signal interacting with a historical positioning terminal device, wherein the signal characteristics include: signal strength and frequency offset;

[0032] Calculate the initial ranging result based on the propagation time of the transmitted signal or received signal interacting with the historical positioning terminal device;

[0033] The initial distance measurement results, signal characteristics and corresponding true distance values ​​are input into a convolutional neural network for training to obtain a distance correction model based on deep learning.

[0034] In a second aspect, a high-precision positioning system is provided, the system comprising:

[0035] Multi-antenna array module: used to use the multi-antenna array of the base station positioning terminal to exchange signals with the target terminal device to be located, the base station positioning terminal transmits signals to the target terminal device to be located and the base station positioning terminal receives signals from the target terminal device to be located;

[0036] Direction finding module: used to calculate the phase difference based on the transmitted signal or received signal when the multi-antenna array interacts with the target terminal device to be located, extract the characteristics of the received signal or transmitted signal, and calculate the first direction of the target terminal to be located based on a pre-built deep learning-based direction enhancement model; the characteristics of the received signal or transmitted signal include signal strength and frequency offset; use the attenuation model and the signal strength of the current received signal or transmitted signal to estimate the second direction of the target terminal to be located, and perform a weighted sum of the first and second directions of the target terminal to be located to obtain the final direction;

[0037] Ranging module: used to obtain the propagation time of the received signal or transmitted signal of each antenna based on the transmitted signal or received signal when the multi-antenna array interacts with the target terminal device to be located, so as to calculate the initial ranging result with the target terminal to be located, and extract the characteristics of the received signal and the transmitted signal, and use the initial ranging result and the characteristics of the received signal and the transmitted signal to correct the initial ranging result based on a pre-built deep learning-based distance correction model to obtain a first ranging result; use the attenuation model and the signal strength of the current received signal or transmitted signal to estimate the second distance of the target terminal to be located, and perform a weighted sum of the first ranging result and the second ranging result of the target terminal to be located to obtain a final distance;

[0038] Data processing module: used to calculate the initial location information of the target terminal device based on the final direction and final distance of the target terminal to be located; and correct the initial location information of the target terminal device in combination with the initial location information of the target terminal device calculated by multiple base station positioning terminals to obtain the final positioning information.

[0039] In a third aspect, a computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the high-precision positioning method described in the first aspect are implemented.

[0040] In a fourth aspect, a computer program product includes a computer program / instruction, which, when executed by a processor, implements the steps of the high-precision positioning method described in the first aspect.

[0041] This application has at least the following beneficial effects:

[0042] This application uses a multi-antenna array to interact with the target terminal device to be located, and calculates direction and distance based on the phase difference and propagation time of the transmitted or received signal, achieving centimeter-level or even millimeter-level positioning accuracy. It also uses deep learning algorithms and dynamic adjustment mechanisms to calculate direction and distance, effectively addressing multipath effects and signal attenuation, ensuring high reliability in complex environments, and improving the accuracy of direction and distance calculations, thereby improving the accuracy of position calculations. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flowchart of a high-precision positioning method provided in one embodiment of the present application;

[0044] Figure 2 A schematic diagram of a specific direction finding process is provided for an embodiment of the present application;

[0045] Figure 3 This is a schematic diagram of a specific flow chart of ranging in one embodiment of the present application;

[0046] Figure 4 A flowchart of a high-precision positioning method is provided for one embodiment of the present application.

[0047] Figure 5 A block diagram of the module architecture of a high-precision positioning system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0049] In one embodiment, Figure 1 As shown, a high-precision positioning method is provided, comprising the following steps:

[0050] Step S1: Use the base station positioning terminal multi-antenna array to interact with the target terminal device to be located, and obtain the base station positioning terminal transmitting signals to the target terminal device to be located and the base station positioning terminal receiving signals from the target terminal device to be located.

[0051] In step S1, the base station positioning terminal is equipped with a massive MIMO antenna array and supports beamforming technology, which can generate directional beams and enhance signal quality. It also uses an adaptive beam adjustment algorithm to dynamically optimize the beam direction to adapt to the movement of the terminal device to be positioned and changes in complex environments, thereby improving the stability and accuracy of direction and ranging.

[0052] Step S2: Calculate the phase difference based on the transmitted signal or received signal when the multi-antenna array interacts with the target terminal device to be located, extract the characteristics of the received signal or the transmitted signal, and calculate the first direction of the target terminal to be located based on a pre-built deep learning-based direction enhancement model; the characteristics of the received signal or the transmitted signal include signal strength and frequency offset; use the attenuation model and the signal strength of the current received signal or the transmitted signal to estimate the second direction of the target terminal to be located, and perform weighted sum on the first direction and the second direction of the target terminal to be located to obtain the final direction.

[0053] In step S2, if Figure 2 Figure 2 shows the specific process of direction finding. This introduces improved Angle of Arrival (AoA) and Angle of Departure (AoD) technologies, combined with machine learning algorithms to correct the direction of signal calculations, effectively improving direction finding accuracy.

[0054] When receiving signals, an adaptive beam adjustment algorithm based on the gradient descent method is used to dynamically optimize the beam direction to enhance the strength of the received signal. Its mathematical model is:

[0055]

[0056] Where w is the beam weight vector, y is the received signal, is the channel matrix. Through this algorithm, the system can adjust the beam direction in real time according to the location changes of the terminal device to improve signal quality.

[0057] Real-time beam adjustment: The adaptive beam adjustment algorithm dynamically adjusts the beam direction based on the location of the terminal device, ensuring that the beam remains aligned with the terminal. This real-time adjustment capability helps improve the accuracy and robustness of direction finding, especially in multipath environments or with mobile devices. Improved signal quality: By optimizing beam weights, the received signal strength is enhanced and the effects of noise and interference are reduced, providing a higher-quality input signal to the direction finding module. This higher-quality signal helps reduce errors in direction finding and improves the accuracy of direction estimation.

[0058] At the same time, multi-band signal processing technology can also be used to reduce the impact of multipath effects and environmental interference based on the propagation characteristics of signals in different frequency bands, thereby ensuring the accuracy of direction estimation.

[0059] In addition, a deep learning-based direction enhancement model is adopted to predict the impact of multipath effects by training a convolutional neural network (CNN) and dynamically compensate for the direction.

[0060] The working process included in step S2:

[0061] The positioning terminal device sends uplink signals and the antenna array receives the signals.

[0062] Analyze the signal phase difference and calculate the direction of the terminal device.

[0063] Output direction information.

[0064] Step S3: Obtain the propagation time of the received signal or transmitted signal of each antenna according to the transmitted signal or received signal when the multi-antenna array interacts with the target terminal device to be located, so as to calculate the initial ranging result with the target terminal to be located, and extract the features of the received signal and the transmitted signal, and use the initial ranging result and the features of the received signal and the transmitted signal to correct the initial ranging result based on a pre-built deep learning-based distance correction model to obtain a first ranging result; use the attenuation model and the signal strength of the current received signal or transmitted signal to estimate the second distance of the target terminal to be located, and perform a weighted sum of the first ranging result and the second ranging result of the target terminal to be located to obtain a final distance.

[0065] In step S3, an improved round-trip time method (RTT) and time difference method (ToA / TDoA) are used in combination with distributed time synchronization technology to calculate the initial ranging result, thereby ensuring a high degree of accuracy of the ranging result.

[0066] When measuring distance, a high-precision clock module is used to record the signal propagation time, and the distance is calculated using the following formula:

[0067] d=c·Δt

[0068] Where d is the distance between the terminal and the terminal device, c is the speed of light, and Δt is the signal propagation time.

[0069] Distributed time synchronization technology is also introduced to ensure time consistency among multiple terminals. The synchronization formula is:

[0070] T sync =T local +ΔT

[0071] Among them, T sync is the synchronization time, T local is the local time, and ΔT is the time deviation. Through this technology, the system significantly reduces the ranging error.

[0072] In addition, the system also introduces a signal strength compensation mechanism, whose mathematical model is:

[0073] P r (d) = P t +G t +G r -20log 10 (d)-L f

[0074] Among them, (x, y) is the terminal device position to be solved, (x i ,y i ) is the position of the i-th terminal, d i It is the distance between the terminal and the terminal device.

[0075] By analyzing the signal attenuation model, the ranging error caused by environmental changes can be dynamically corrected to further improve the measurement accuracy.

[0076] Therefore, the accuracy of ranging results is ensured by combining improved RTT technology with distributed time synchronization. High-precision clock modules and edge computing technology are used to reduce latency.

[0077] The working process of step S3 is as follows:

[0078] The base station positioning terminal sends a signal, and the terminal device to be positioned receives it and returns a response signal.

[0079] Record the signal propagation time and calculate the distance based on the signal propagation speed.

[0080] Output distance information.

[0081] Step S4: Calculate the initial location information of the target terminal device based on the final direction and final distance of the target terminal to be located; and correct the initial location information of the target terminal device based on the initial location information calculated by multiple base station positioning terminals to obtain the final positioning information.

[0082] In step S4, multiple base station positioning terminals work together to measure the direction and distance of the terminal device. The direction and distance measurement results of multiple terminals are integrated and the specific location of the terminal device is calculated using a geometric algorithm.

[0083] Algorithm details: The data processing unit adopts a geometric positioning algorithm based on the least squares method, and its mathematical model is:

[0084]

[0085] Among them, (x, y) is the terminal device position to be solved, (x i ,y i ) is the position of the i-th terminal, di The distance between the terminal and the terminal device. Through this algorithm, the system can quickly calculate the precise location of the terminal device in a complex environment.

[0086] At the same time, distributed time synchronization technology is introduced to ensure time consistency among multiple terminals.

[0087] Utilize edge computing technology to complete data processing locally on the terminal and reduce latency.

[0088] Working process of step S4:

[0089] Multiple base station positioning terminals respectively receive uplink signals of the target terminal device to be positioned.

[0090] Each base station positioning terminal independently measures the direction and distance of the terminal device.

[0091] The data processing center integrates the results of multiple terminals and calculates the location of the terminal device through geometric algorithms.

[0092] Output the final positioning information.

[0093] In this embodiment, the following steps are included:

[0094] 1. Direction finding:

[0095] The terminal receives the uplink signal from the terminal device through the antenna array, and combines the improved AoA / AoD technology and machine learning algorithm to accurately calculate the direction of the signal source.

[0096] Multi-band signal processing technology is used to reduce the impact of multipath effects and ensure the accuracy of direction estimation.

[0097] 2. Distance measurement:

[0098] The terminal measures the signal propagation time through the improved RTT / ToA technology and combines it with the signal strength compensation mechanism to accurately calculate the distance between the terminal and the terminal device.

[0099] The application of distributed time synchronization technology and signal attenuation model further improves the reliability and accuracy of ranging results.

[0100] 3. Positioning:

[0101] The data processing unit integrates the direction finding and ranging results and calculates the specific location of the terminal device through geometric algorithms.

[0102] The application of edge computing technology enables the positioning process to be completed quickly locally on the terminal, significantly reducing latency and meeting real-time requirements.

[0103] In the multi-terminal collaborative positioning scenario, the positioning accuracy is further improved by fusing data from multiple terminals.

[0104] Advantages of this application include:

[0105] High precision: Through improved AoA / AoD technology and RTT / ToA algorithm, combined with multi-band signal processing and environmental compensation, centimeter-level or even millimeter-level positioning accuracy is achieved.

[0106] Strong environmental adaptability: Utilizes deep learning algorithms and dynamic adjustment mechanisms to effectively address multipath effects and signal attenuation, ensuring high reliability in complex environments.

[0107] Low latency: The application of edge computing technology enables data processing to be completed locally on the terminal, significantly shortening the time for positioning output.

[0108] Low cost: Fully utilizes existing 5G terminal hardware resources, eliminating the need to deploy additional expensive equipment and reducing system implementation costs.

[0109] Through the above-mentioned optimized design and technical solutions, the present invention provides 5G terminals with more efficient and accurate direction and ranging capabilities.

[0110] In one embodiment, the deep learning-based direction enhancement model is constructed by the following method:

[0111] Obtain the historical transmission or reception signals of the positioning terminal device interacting with the multi-array antenna, and obtain the actual signal direction of the positioning terminal device obtained through high-precision equipment calibration;

[0112] Extracting characteristics of a transmitted signal or a received signal interacting with a historical positioning terminal device, wherein the signal characteristics include: signal strength and frequency offset;

[0113] Calculate and extract the phase difference of the transmitted signal or received signal interacting with the historical positioning terminal device;

[0114] The phase difference between the transmitted signal and the received signal interacting with the historical positioning terminal device, the signal characteristics and the corresponding real signal direction are input into the convolutional neural network for training to obtain a direction enhancement model based on deep learning.

[0115] In one embodiment, the use of a multi-antenna array to perform signal interaction with the target terminal device to be located also includes: using multi-band signal processing technology to use multiple frequency bands to perform signal interaction with the target terminal device to be located to obtain transmission signals and reception signals in different frequency bands.

[0116] In one embodiment, the attenuation model is constructed by the following formula:

[0117] P r (d) = P t +G t +G r -20log 10 (d)-L f

[0118] Among them, P r (d) is the received power, which represents the signal power received at a distance of d. t : Transmit Power, which indicates the initial power when the transmitter sends the signal; G t : Transmit Antenna Gain, which indicates the amplification factor of the transmitting antenna on the signal; G r : Receive Antenna Gain, which indicates the amplification factor of the signal by the receiving antenna; d: the distance between the transmitter and the receiver; 20log 10 (d) Free Space Path Loss, which indicates the law of signal attenuation as the distance increases in free space, L f : Additional Loss, which refers to other loss factors besides free space path loss.

[0119] In one embodiment, when using a multi-antenna array to perform signal interaction with a target terminal device to be located, a distributed time synchronization technology is used to ensure time consistency among multiple multi-antenna arrays.

[0120] In one embodiment, the initial location information of the target terminal device calculated by multiple base station positioning terminals is corrected to obtain the final positioning information, including:

[0121] The final location information of the target terminal is calculated using the following formula:

[0122]

[0123] Among them, (x, y) is the terminal device position to be solved, (x i ,y i ) is the position of the i-th terminal, d i The distance between the terminal and the terminal device. Through this algorithm, the system can quickly calculate the precise location of the terminal device in a complex environment.

[0124] In one embodiment, the pre-built deep learning-based distance correction model is constructed by the following method:

[0125] Obtain the historical transmission or reception signals of the interaction between the positioning terminal device and the multi-array antenna, and obtain the actual distance value of the positioning terminal device obtained through high-precision equipment calibration;

[0126] Extracting characteristics of a transmitted signal or a received signal interacting with a historical positioning terminal device, wherein the signal characteristics include: signal strength and frequency offset;

[0127] Calculate the initial ranging result based on the propagation time of the transmitted signal or received signal interacting with the historical positioning terminal device;

[0128] The initial distance measurement results, signal characteristics and corresponding true distance values ​​are input into a convolutional neural network for training to obtain a distance correction model based on deep learning.

[0129] In one embodiment, a high-precision positioning system is provided, comprising:

[0130] Multi-antenna array module: used to use the multi-antenna array of the base station positioning terminal to exchange signals with the target terminal device to be located, the base station positioning terminal transmits signals to the target terminal device to be located and the base station positioning terminal receives signals from the target terminal device to be located;

[0131] Direction finding module: used to calculate the phase difference based on the transmitted signal or received signal when the multi-antenna array interacts with the target terminal device to be located, extract the characteristics of the received signal or transmitted signal, and calculate the first direction of the target terminal to be located based on a pre-built deep learning-based direction enhancement model; the characteristics of the received signal or transmitted signal include signal strength and frequency offset; use the path loss model and the signal strength of the current received signal or transmitted signal to estimate the second direction of the target terminal to be located, and perform a weighted sum of the first and second directions of the target terminal to be located to obtain the final direction;

[0132] Ranging module: used to obtain the propagation time of the received signal or transmitted signal of each antenna based on the transmitted signal or received signal when the multi-antenna array interacts with the target terminal device to be located, so as to calculate the initial ranging result with the target terminal to be located, and extract the characteristics of the received signal and the transmitted signal, and use the initial ranging result and the characteristics of the received signal and the transmitted signal to correct the initial ranging result based on a pre-built deep learning-based distance correction model to obtain a first ranging result; use the path loss model and the signal strength of the current received signal or transmitted signal to estimate the second distance of the target terminal to be located, and perform a weighted sum of the first ranging result and the second ranging result of the target terminal to be located to obtain a final distance;

[0133] Data processing module: used to calculate the initial location information of the target terminal device based on the final direction and final distance of the target terminal to be located; and correct the initial location information of the target terminal device in combination with the initial location information of the target terminal device calculated by multiple base station positioning terminals to obtain the final positioning information.

[0134] The working process of this application is:

[0135] The base station positioning terminal receives the uplink signal of the terminal device to be positioned through the antenna array.

[0136] The direction finding module analyzes the phase difference of the signal and calculates the direction of the terminal device to be located.

[0137] The ranging module measures the signal propagation time and calculates the distance between the base station positioning terminal and the terminal device to be positioned.

[0138] The data processing unit integrates the direction finding and ranging results and calculates the specific location of the terminal device through geometric algorithms.

[0139] The environmental compensation module corrects the results and outputs the final positioning information.

[0140] For the specific definition of a high-precision positioning system, please refer to the definition of a high-precision positioning method above and will not be repeated here. Each module in the above-mentioned high-precision positioning system can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0141] In one embodiment, a computer device is provided, which may be a server. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is configured to communicate with an external terminal via a network connection. When executed by the processor, the computer program implements the aforementioned high-precision positioning method.

[0142] In one embodiment, a computer-readable storage medium is further provided, on which a computer program is stored, which involves all or part of the processes in the above-mentioned embodiment method.

[0143] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0144] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0145] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A high-precision positioning method, characterized in that: The method comprises: Using a base station positioning terminal multi-antenna array to perform signal interaction with a target terminal device to be located, obtaining signals transmitted by the base station positioning terminal to the target terminal device to be located and signals received by the base station positioning terminal from the target terminal device to be located; Calculating a phase difference based on a transmitted signal or a received signal when the multi-antenna array interacts with the target terminal device to be located, extracting features of the received signal or the transmitted signal, and calculating a first direction of the target terminal to be located based on a pre-built deep learning-based direction enhancement model; the features of the received signal or the transmitted signal include signal strength and frequency offset; estimating a second direction of the target terminal to be located using an attenuation model and the signal strength of the current received signal or the transmitted signal, and performing a weighted sum of the first and second directions of the target terminal to be located to obtain a final direction; Obtaining the propagation time of the received signal or transmitted signal of each antenna according to the transmitted signal or received signal when the multi-antenna array interacts with the target terminal device to be located, so as to calculate the initial ranging result with the target terminal to be located, and extracting the features of the received signal and the transmitted signal, and using the initial ranging result and the features of the received signal and the transmitted signal to correct the initial ranging result based on a pre-built deep learning-based distance correction model to obtain a first ranging result; using the attenuation model and the signal strength of the current received signal or transmitted signal to estimate the second distance of the target terminal to be located, and performing a weighted sum of the first ranging result and the second ranging result of the target terminal to be located to obtain a final distance; The initial position information of the target terminal device is calculated based on the final direction and final distance of the target terminal to be located; and the initial position information of the target terminal device calculated by multiple base station positioning terminals is corrected to obtain the final positioning information.

2. The method according to claim 1, characterized in that The deep learning-based direction enhancement model is constructed by the following method: Obtain the historical transmission or reception signals of the positioning terminal device interacting with the multi-array antenna, and obtain the actual signal direction of the positioning terminal device obtained through high-precision equipment calibration; Extracting characteristics of a transmitted signal or a received signal interacting with a historical positioning terminal device, wherein the signal characteristics include: signal strength and frequency offset; Calculate and extract the phase difference of the transmitted signal or received signal interacting with the historical positioning terminal device; The phase difference between the transmitted signal and the received signal interacting with the historical positioning terminal device, the signal characteristics and the corresponding real signal direction are input into the convolutional neural network for training to obtain a direction enhancement model based on deep learning.

3. The method according to claim 1, characterized in that The use of a multi-antenna array to perform signal interaction with the target terminal device to be located also includes: using multi-band signal processing technology to use multiple frequency bands to perform signal interaction with the target terminal device to be located to obtain transmission signals and reception signals in different frequency bands.

4. The method according to claim 1, wherein The attenuation model is constructed by the following formula: P r (d)=P t +G t +G r -20log 10 (d)-L f Among them, P r (d) is the received power, P t is the transmission power, G t is the transmitting antenna gain, G r is the receiving antenna gain, d is the distance between the transmitter and the receiver, 20log 10 (d) is the free space path loss, L f For additional loss.

5. The method according to claim 1, wherein When the multi-antenna array is used to perform signal interaction with the target terminal device to be located, the distributed time synchronization technology is used to ensure the time consistency between the multiple multi-antenna arrays.

6. The method according to claim 1, characterized in that The initial location information of the target terminal device calculated by the plurality of base station positioning terminals is corrected to obtain the final positioning information, including: The final location information of the target terminal is calculated using the following formula: Among them, (x, y) is the terminal device position to be solved, (x i ,y i ) is the position of the i-th terminal, d i It is the distance between the terminal and the terminal device.

7. The method according to claim 1, characterized in that The pre-built deep learning-based distance correction model is constructed by the following method: Obtain the historical transmission or reception signals of the interaction between the positioning terminal device and the multi-array antenna, and obtain the actual distance value of the positioning terminal device obtained through high-precision equipment calibration; Extracting characteristics of a transmitted signal or a received signal interacting with a historical positioning terminal device, wherein the signal characteristics include: signal strength and frequency offset; Calculate the initial ranging result based on the propagation time of the transmitted signal or received signal interacting with the historical positioning terminal device; The initial distance measurement results, signal characteristics and corresponding true distance values ​​are input into a convolutional neural network for training to obtain a distance correction model based on deep learning.

8. A high-precision positioning system, characterized in that: The system comprises: Multi-antenna array module: used to use the multi-antenna array of the base station positioning terminal to exchange signals with the target terminal device to be located, the base station positioning terminal transmits signals to the target terminal device to be located and the base station positioning terminal receives signals from the target terminal device to be located; Direction finding module: used to calculate the phase difference based on the transmitted signal or received signal when the multi-antenna array interacts with the target terminal device to be located, extract the characteristics of the received signal or transmitted signal, and calculate the first direction of the target terminal to be located based on a pre-built deep learning-based direction enhancement model; the characteristics of the received signal or transmitted signal include signal strength and frequency offset; use the attenuation model and the signal strength of the current received signal or transmitted signal to estimate the second direction of the target terminal to be located, and perform a weighted sum of the first and second directions of the target terminal to be located to obtain the final direction; Ranging module: used to obtain the propagation time of the received signal or transmitted signal of each antenna based on the transmitted signal or received signal when the multi-antenna array interacts with the target terminal device to be located, so as to calculate the initial ranging result with the target terminal to be located, and extract the characteristics of the received signal and the transmitted signal, and use the initial ranging result and the characteristics of the received signal and the transmitted signal to correct the initial ranging result based on a pre-built deep learning-based distance correction model to obtain a first ranging result; use the attenuation model and the signal strength of the current received signal or transmitted signal to estimate the second distance of the target terminal to be located, and perform a weighted sum of the first ranging result and the second ranging result of the target terminal to be located to obtain a final distance; Data processing module: used to calculate the initial location information of the target terminal device based on the final direction and final distance of the target terminal to be located; and correct the initial location information of the target terminal device in combination with the initial location information of the target terminal device calculated by multiple base station positioning terminals to obtain the final positioning information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images