Positioning method and system based on blind source signal separation technology

Abstract

The invention relates to a positioning method and system based on a blind source signal separation technology, and the method comprises the following steps: collecting blind source signals of all measurement points, and constructing a detection matrix; preprocessing the detection matrix, wherein the preprocessing comprises centralization and whitening processing; performing natural gradient descent operation on the preprocessed detection matrix, calculating a gradient matrix, and realizing radio frequency separation through the gradient matrix; calculating the distance between the blind source signal node after radio frequency separation and the measurement point by using a radio frequency space attenuation model; and calculating blind source signal space coordinates according to the space distribution probability model and the distance between the blind source signal node and the measurement point. The method can achieve the positioning of stored articles in a three-dimensional space in a complex signal environment.

Description

Technical Field

[0001] The present application relates to the technical field of blind source separation signal processing, and more specifically, to a positioning method and system based on blind source signal separation technology. Background Art

[0002] my country's modern supply chain industry is developing rapidly, and logistics warehousing technology is gradually developing rapidly in the direction of automation and intelligence. How to efficiently find and accurately locate the physical location of a large number of stored items has become one of the important factors affecting the efficiency of storage warehouses. With the advancement of the construction of new power systems, power companies have attached RFID tags to a large number of electricity meters, collection terminals, concentrators, etc., and used RFID reading and writing recognition technology to identify and manage the power materials entering and leaving the warehouse, solving the problem of asset inventory and verification management of power materials. However, this technology does not have the ability to identify and accurately locate materials, and cannot solve the requirements for accurate picking of power materials when entering and leaving the warehouse, limiting the application efficiency of automated warehousing. Technologies such as UWB are also commonly used for indoor positioning, but such technologies have active terminals and require support from the main station, which is costly and not conducive to large-scale application.

[0003] With the development of modern science and technology, the requirements for the positioning accuracy and reliability of targets in three-dimensional space are getting higher and higher. For example, in the fields of indoor positioning, virtual reality, augmented reality, drone navigation, robot autonomous positioning, etc., it is crucial to accurately obtain the position information of the target in three-dimensional space. Traditional positioning methods may be limited by many factors, such as signal interference, multipath propagation, environmental complexity, etc., so new technical means are needed to improve positioning performance.

[0004] Prior art, such as the Chinese patent with patent number "CN109143164A", discloses a wireless signal source positioning method based on Gaussian process regression. The invention includes deploying wireless signal detectors, and the location information of all wireless signal detectors forms a matrix X; each wireless signal detector collects received signal strength information and exchanges information with each other, and all received signal strength information forms a vector r; the matrix X and the vector r form a training set, a Gaussian process regression model is established, and the hyperparameters in the Gaussian process regression model are solved according to the training set to obtain the established Gaussian process regression model; the established Gaussian process regression model is used to predict the received signal strength information at the new position, complete the prediction of the received signal strength distribution of the entire area of ​​interest, and obtain the position of the signal emission source. The present invention is suitable for locating the position of the signal emission source.

[0005] The problem with the above-mentioned prior art is that Gaussian process regression is based on some specific assumptions, such as the relationship between signal strength and position conforms to a specific probability distribution. However, in actual environments, this assumption may not be completely true, especially in complex indoor environments or environments with severe multipath propagation, where the propagation characteristics of the signal may be more complex and changeable, resulting in a decrease in the prediction ability of the model. And as the number of wireless signal detectors increases or the area of ​​interest expands, the complexity of the model will further increase, which may lead to a sharp increase in computing resources and storage requirements, limiting the application of the method in large-scale scenarios. Summary of the invention

[0006] In order to solve the above technical problems, the present invention proposes a positioning method and system based on blind source signal separation technology.

[0007] The technical solution of the present invention is as follows:

[0008] The present invention proposes a positioning method based on blind source signal separation technology, comprising the following steps:

[0009] Step S1, collecting blind source signals at each measurement point and constructing a detection matrix;

[0010] Step S2, preprocessing the detection matrix, including centering and whitening processing;

[0011] Step S3, performing a natural gradient descent operation on the preprocessed detection matrix, calculating a gradient matrix, and realizing radio frequency separation through the gradient matrix;

[0012] Step S4, using a radio frequency spatial attenuation model to calculate the distance between the blind source signal node and the measurement point after radio frequency separation;

[0013] Step S5, calculating the blind source signal spatial coordinates according to the spatial distribution probability model and the distance between the blind source signal node and the measurement point.

[0014] As a preferred implementation, in the step of collecting blind source signals at each measurement point and constructing a detection matrix, the detection matrix is ​​specifically expressed as:

[0015]

[0016] Where: is the signal detected at the mth measurement point; X m，n The nth signal detected at the mth measurement point.

[0017] As a preferred implementation, the preprocessing of the detection matrix includes centering and whitening processing; specifically, it includes the following process:

[0018] The specific formula of the centralized detection matrix is ​​as follows:

[0019]

[0020] Where: X i，j represents the element in row i and column j; X c is the detection matrix after centralization;

[0021] The centralized detection matrix is ​​whitened. The specific formula is as follows:

[0022] X w =W whitening *X c

[0023] Where: W whitening is the whitening matrix.

[0024] As a preferred implementation, the natural gradient descent operation is performed on the preprocessed detection matrix, the gradient matrix is ​​calculated, and the RF separation is realized by the gradient matrix, which specifically includes the following steps:

[0025] Initialize the gradient matrix. The specific formula is as follows:

[0026] W=Rand()

[0027] In the formula, Rand() is used to generate a random matrix;

[0028] Perform decorrelation operation on the initialized gradient matrix. The specific formula is as follows:

[0029]

[0030] Update the gradient matrix according to the preprocessed detection matrix. The specific formula is as follows:

[0031]

[0032] Where: S = W * X w ;X w is the detection matrix after preprocessing; For X w The transposed matrix of S; g(S) = tanh(S) is the hyperbolic tangent function of S; g′(S) = 1-g 2 (S) is the first-order derivative function;

[0033] W new is the updated gradient matrix;

[0034] Perform decorrelation operation on the updated gradient matrix. The specific formula is as follows:

[0035]

[0036] Check whether the gradient matrix difference norm converges. The specific formula is as follows:

[0037]

[0038] Where p, q are W matrix elements, W is an h×h matrix, q, p∈h; if the gradient matrix difference norm is not close to 0, it means no convergence, then repeat the gradient matrix update step; if the gradient matrix difference norm is close to 0, it means convergence, then exit the loop;

[0039] In the RF signal separation stage, RF separation is performed through the gradient matrix whose gradient matrix difference norm has converged. The specific calculation formula of the separated signal matrix is ​​as follows:

[0040]

[0041] Where, Y is the separated signal matrix; is the transposed matrix of the gradient matrix.

[0042] As a preferred implementation, the distance between the blind source signal node and the measurement point after radio frequency separation is calculated using the radio frequency spatial attenuation model, and the specific calculation formula is as follows:

[0043]

[0044] in:

[0045] R m，n =Coef m *y m,n

[0046] In the formula, R m,n y is the signal transmission loss from the measurement point m to the signal source n; m,n Coef is the signal transmission loss of signal source n separated from the RF signal at measurement point m; m is the signal quantization coefficient of the measurement point m; M n is the RF frequency of signal source n.

[0047] As a preferred implementation, the method of calculating the blind source signal spatial coordinates according to the spatial distribution probability model and the distance between the blind source signal node and the measurement point comprises the following steps:

[0048] Calculate the sphere with the measuring point m as the center and radius D m,n +delta distribution space function:

[0049] Sp m (delta)=Sphere(Pos m , D m，n +delta)

[0050] In the formula, Sphere(Pos m , Dm，n +delta) to find Pos m Center, D m，n +delta is the spatial spherical coordinate of the radius; Pos m is the spatial coordinate of the measuring point m; delta is the displacement change;

[0051] Calculate the spatial overlap function of m distribution spaces:

[0052] s(delta)=Mutex(Sp 1 , …, Sp m )

[0053] In the formula, Mutex(Sp 1 , …, Sp m )To seek Sp 1 , …, Sp m The amount of spatial overlap; delta is the displacement change;

[0054] Solve the minimum value of the distribution space loss function:

[0055]

[0056] In the formula, is the distribution space loss function;

[0057] Calculate the blind source signal positioning coordinates:

[0058] Tarpos=Crd(Pos m , D m，n +DELTA min )

[0059] In the formula, Crd(Pos m , D m，n +DELTA) is the distance D from the m measurement point coordinates to the corresponding signal source n m,n +DELTA min , calculate the spatial coordinates of the blind source signal.

[0060] On the other hand, the present invention also provides a positioning system based on blind source signal separation technology, comprising:

[0061] The detection matrix construction module collects blind source signals at each measurement point and constructs a detection matrix;

[0062] The preprocessing module preprocesses the detection matrix, including centering and whitening;

[0063] The RF separation module performs a natural gradient descent operation on the preprocessed detection matrix, calculates the gradient matrix, and realizes RF separation through the gradient matrix;

[0064] The distance calculation module uses the RF spatial attenuation model to calculate the distance between the blind source signal node and the measurement point after RF separation;

[0065] The three-dimensional positioning module calculates the spatial coordinates of the blind source signal based on the spatial distribution probability model and the distance between the blind source signal node and the measurement point.

[0066] As a preferred implementation, the detection matrix construction module collects blind source signals at each measurement point and constructs a detection matrix: the detection matrix is ​​specifically expressed as:

[0067]

[0068] Where: is the signal detected at the mth measurement point; X m,n The nth signal detected at the mth measurement point.

[0069] On the other hand, the present invention further provides an electronic device having a computer program stored thereon, wherein when the computer program is executed by a processor, a positioning method based on blind source signal separation technology as described in any embodiment of the present invention is implemented.

[0070] On the other hand, the present invention also provides a computer-readable medium for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement a positioning method based on blind source signal separation technology as described in any embodiment of the present invention.

[0071] The present invention has the following beneficial effects:

[0072] 1. The measurement point arrangement is simple and convenient. Arranging multiple measurement points provides a richer source of signal characteristics. By constructing a detection matrix, the signal characteristics of different positions can be comprehensively considered, providing a more comprehensive basis for subsequent processing and analysis, which is suitable for large-scale promotion and application.

[0073] 2. In the RF separation problem, signals often have high dimensions and complex correlations. The natural gradient descent algorithm can more effectively find the optimal solution and achieve more accurate RF separation. By combining the signals after RF separation, the influence of other interference signals can be eliminated and the location of the blind source signal node can be determined more accurately.

[0074] 3. The RF spatial attenuation model takes into account the propagation characteristics of the signal in space and can more accurately estimate the distance between the signal source and the measurement point.

[0075] 4. The spatial distribution probability model takes into account the distribution law of the signal in space and can estimate the location of the signal source more accurately. Compared with some positioning technologies based on geometric methods, this model can better adapt to the uncertainty and complexity of the signal and improve the accuracy of coordinate calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0077] Figure 1 is a schematic diagram of the method flow of Example 1,

[0078] Figure 2 This is a schematic diagram of the spatial distribution of the first embodiment;

[0079] Figure 3 This is a natural gradient descent flow chart of the present invention;

[0080] Figure 4 It is the flow chart of spatial positioning of the present invention. DETAILED DESCRIPTION

[0081] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0082] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0083] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0084] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0085] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0086] Embodiment 1:

[0087] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be combined with the specific embodiments of the present application and refer to the attached Figure 1 , clearly and completely describe the technical solution of the present invention.

[0088] To solve the problems in the prior art, the present invention provides a positioning method based on blind source signal separation technology, comprising the following steps:

[0089] Step S1, collecting blind source signals at each measurement point and constructing a detection matrix;

[0090] like Figure 2 As shown, the signal is detected at measurement point 1 Signal detected at measurement point 2 Then construct the detection matrix:

[0091]

[0092] Where: is the signal detected at the mth measurement point; X m，n The nth signal detected at the mth measurement point.

[0093] Step S2, preprocessing the detection matrix, including centering and whitening processing;

[0094] Step S201, centralize the detection matrix. The specific formula of the centralized detection matrix is ​​as follows:

[0095]

[0096] Where: X i，j represents the element in row i and column j; X c is the detection matrix after centralization;

[0097] Step S202, whitening the centralized detection matrix, the specific formula is as follows:

[0098] X w =W whitening *X c

[0099] Where: W whitening is the whitening matrix.

[0100] Step S3, performing a natural gradient descent operation on the preprocessed detection matrix, calculating a gradient matrix, and realizing radio frequency separation through the gradient matrix;

[0101] Step S301, initialize the gradient matrix, the specific formula is as follows:

[0102] W=Rand()

[0103] In the formula, Rand() is used to generate a random matrix;

[0104] Step S302, decorrelation gradient matrix, the specific formula is as follows:

[0105]

[0106] Step S303, update the gradient matrix, the specific formula is as follows:

[0107]

[0108] Where: S = W * X w ; For X w Transpose matrix; g(S) = tanh(S) is the hyperbolic tangent function of S; g′(S) = 1-g 2 (S) is the first-order derivative function;

[0109] Step S304, decorrelation gradient matrix, the specific formula is as follows:

[0110]

[0111] Step S305, check whether the gradient matrix difference norm converges, the specific formula is as follows:

[0112]

[0113] Where p, q are W matrix elements, W is h ×h order matrix, q, p ∈ h; if the gradient matrix difference norm is not close to 0, it means no convergence, then repeat to update the gradient matrix step; if the gradient matrix difference norm is close to 0, it means convergence, then exit the loop;

[0114] Step S306, RF signal separation step, the specific formula is as follows:

[0115]

[0116] Where, Y is the separated signal matrix; is the transposed matrix of the gradient matrix.

[0117] Step S4, using a radio frequency spatial attenuation model to calculate the distance between the blind source signal node and the measurement point after radio frequency separation;

[0118] According to the RF spatial attenuation model, the formula for calculating the distance between the blind source signal node and the measurement point is as follows:

[0119]

[0120] in:

[0121] R m，n =Coef m *y m,n

[0122] In the formula, R m,n y is the signal transmission loss from the measurement point m to the signal source n; m,n Coef is the signal transmission loss of signal source n separated from the RF signal at measurement point m; m is the signal quantization coefficient of the measurement point m; M n is the radio frequency frequency of the signal source n. Step S5, calculating the blind source signal spatial coordinates according to the spatial distribution probability model and the distance between the blind source signal node and the measurement point.

[0123] Step S501, calculate the sphere with the measuring point m as the center and the radius D m,n +delta distribution space function:

[0124] Sp m (delta)=Sphere(Pos m , D m，n +delta)

[0125] In the formula, Sphere(Pos m , D m，n +delta) to find Pos m Center, D m，n +delta is the spatial spherical coordinate of the radius; Pos m is the spatial coordinate of the measuring point m; delta is the displacement change;

[0126] Step S502, calculating the spatial overlap function of m distribution spaces:

[0127] s(delta)=Mutex(Sp 1 , …, Sp m )

[0128] In the formula, Mutex(Sp 1 , …, Sp m )To seek Sp 1 , …, Sp m The amount of spatial overlap; delta is the displacement change;

[0129] Step S503, solving the minimum value of the distribution space loss function:

[0130]

[0131] In the formula, is the distribution space loss function;

[0132] Step S504, calculate the blind source signal positioning coordinates:

[0133] Tarpos=Crd(Pos m , D m，n +DELTA min )

[0134] In the formula, Crd(Pos m , D m，n +DELTA) is the distance D from the m measurement point coordinates to the corresponding signal source n m,n +DELTA min , calculate the spatial coordinates of the blind source signal.

[0135] Embodiment 2:

[0136] This embodiment provides a positioning system based on blind source signal separation technology, including:

[0137] The detection matrix construction module collects blind source signals at each measurement point and constructs a detection matrix;

[0138] The preprocessing module preprocesses the detection matrix, including centering and whitening;

[0139] The RF separation module performs a natural gradient descent operation on the preprocessed detection matrix, calculates the gradient matrix, and realizes RF separation through the gradient matrix;

[0140] The distance calculation module uses the RF spatial attenuation model to calculate the distance between the blind source signal node and the measurement point after RF separation;

[0141] The three-dimensional positioning module calculates the spatial coordinates of the blind source signal based on the spatial distribution probability model and the distance between the blind source signal node and the measurement point.

[0142] Embodiment three:

[0143] This embodiment provides an electronic device having a computer program stored thereon. When the computer program is executed by a processor, a positioning method based on blind source signal separation technology as described in any embodiment of the present invention is implemented.

[0144] Embodiment 4:

[0145] This embodiment provides a computer-readable medium for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement a positioning method based on blind source signal separation technology as described in any embodiment of the present invention.

[0146] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0147] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0148] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0149] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0150] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A positioning method based on blind source signal separation technology, characterized in that: The following steps are involved: Step S1, collecting blind source signals at each measurement point and constructing a detection matrix; Step S2, preprocessing the detection matrix, including centering and whitening processing; Step S3, performing a natural gradient descent operation on the preprocessed detection matrix, calculating a gradient matrix, and realizing radio frequency separation through the gradient matrix; Step S4, using a radio frequency spatial attenuation model to calculate the distance between the blind source signal node and the measurement point after radio frequency separation; Step S5, calculating the blind source signal spatial coordinates according to the spatial distribution probability model and the distance between the blind source signal node and the measurement point.

2. The positioning method based on blind source signal separation technology according to claim 1, characterized in that: In the step of collecting blind source signals at each measurement point and constructing a detection matrix, the detection matrix is ​​specifically expressed as: Where: is the signal detected at the mth measurement point; X m,n The nth signal detected at the mth measurement point.

3. The positioning method based on blind source signal separation technology according to claim 2 is characterized in that: The preprocessing of the detection matrix includes centering and whitening processing; specifically, it includes the following processes: The specific formula of the centralized detection matrix is ​​as follows: Where: X i,j represents the element in row i and column j; X c is the detection matrix after centralization; The centralized detection matrix is ​​whitened. The specific formula is as follows: X w =W whitening *X c Where: W whitening is the whitening matrix.

4. The positioning method based on blind source signal separation technology according to claim 1, characterized in that: The method performs a natural gradient descent operation on the preprocessed detection matrix, calculates the gradient matrix, and implements radio frequency separation through the gradient matrix, specifically comprising the following steps: Initialize the gradient matrix. The specific formula is as follows: W=Rand() In the formula, Rand() is used to generate a random matrix; Perform decorrelation operation on the initialized gradient matrix. The specific formula is as follows: Update the gradient matrix according to the preprocessed detection matrix. The specific formula is as follows: Where: S = W * X w ;X w is the detection matrix after preprocessing; For X w The transposed matrix of g(S) = tanh(S) is the hyperbolic tangent function of S; g′(S) = 1-g 2 (S) is the first-order derivative function; W new is the updated gradient matrix; Perform decorrelation operation on the updated gradient matrix. The specific formula is as follows: Check whether the gradient matrix difference norm converges. The specific formula is as follows: Where p, q are W matrix elements, W is an h×h matrix, q, p∈h; if the gradient matrix difference norm is not close to 0, it means no convergence, then repeat to update the gradient matrix step; if the gradient matrix difference norm is close to 0, it means convergence, then exit the loop; In the RF signal separation stage, RF separation is performed through the gradient matrix whose gradient matrix difference norm has converged. The specific calculation formula of the separated signal matrix is ​​as follows: Where, Y is the separated signal matrix; is the transposed matrix of the gradient matrix.

5. The positioning method based on blind source signal separation technology according to claim 1, characterized in that: The distance between the blind source signal node and the measurement point after radio frequency separation is calculated using the radio frequency spatial attenuation model. The specific calculation formula is as follows: in: R m,n =Coef m *y m,n In the formula, R m,n y is the signal transmission loss from the measurement point m to the signal source n; m,n Coef is the signal transmission loss of signal source n separated from the RF signal at measurement point m; m is the signal quantization coefficient of the measurement point m; M n is the RF frequency of signal source n.

6. The positioning method based on blind source signal separation technology according to claim 1, characterized in that: The method of calculating the blind source signal spatial coordinates according to the spatial distribution probability model and the distance between the blind source signal node and the measurement point comprises the following steps: Calculate the sphere with the measuring point m as the center and radius D m,n +delta distribution space function: Sp m (delta)=Sphere(Pos m ,D m,n +delta) In the formula, Sphere(Pos m ,D m,n +delta) to find Pos m Center, D m,n +delta is the spatial spherical coordinate of the radius; Pos m is the spatial coordinate of the measuring point m; delta is the displacement change; Calculate the spatial overlap function of m distribution spaces: s(delta)=Mutex(Sp1,…,Sp m ) In the formula, Mutex(Sp1,…,Sp m )To find Sp1,…,Sp m The amount of spatial overlap; delta is the displacement change; Solve the minimum value of the distribution space loss function: In the formula, is the distribution space loss function; Calculate the blind source signal positioning coordinates: Tarpos=Crd(Pos m ,D m,n +DELTA min ) In the formula, Crd(Pos m ,D m,n +DELTA) is the distance D from the m measurement point coordinates to the corresponding signal source n m,n +DELTA min , calculate the spatial coordinates of the blind source signal.

7. A positioning system based on blind source signal separation technology, characterized in that: include: The detection matrix construction module collects blind source signals at each measurement point and constructs a detection matrix; The preprocessing module preprocesses the detection matrix, including centering and whitening; The RF separation module performs a natural gradient descent operation on the preprocessed detection matrix, calculates the gradient matrix, and realizes RF separation through the gradient matrix; The distance calculation module uses the RF spatial attenuation model to calculate the distance between the blind source signal node and the measurement point after RF separation; The three-dimensional positioning module calculates the spatial coordinates of the blind source signal based on the spatial distribution probability model and the distance between the blind source signal node and the measurement point.

8. The positioning system based on blind source signal separation technology according to claim 7, characterized in that: The detection matrix construction module collects blind source signals at each measurement point and constructs a detection matrix: The detection matrix is ​​specifically expressed as: Where: is the signal detected at the mth measurement point; X m,n The nth signal detected at the mth measurement point.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the positioning method based on blind source signal separation technology as described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the positioning method based on blind source signal separation technology as described in any one of claims 1 to 6 is implemented.

Images