Bluetooth fingerprint positioning method and device, equipment, storage medium and product

Abstract

The invention discloses a Bluetooth fingerprint positioning method and apparatus, a device, a storage medium and a product. The method comprises the steps of obtaining reference point signal data of a plurality of target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points; according to the reference point signal data, constructing a fingerprint point of the target reference point in a fingerprint map; performing positioning calculation on the reference point signal data and the adjacent point signal data to obtain predicted position coordinates of the adjacent point; and according to the deviation between the predicted position coordinate and the actual position coordinate of the adjacent point, performing position fine adjustment on a fingerprint point corresponding to the target reference point in a fingerprint map so as to improve the fingerprint positioning precision of the target reference point. According to the method, the sampling range of the predetermined reference point RSSI is narrowed, the RSSI data of which the position deviates from the reference point is adopted for training, and the position of the reference point is finely adjusted, so that the fingerprint positioning precision is improved.

Description

Technical Field

[0001] The present invention relates to the field of Bluetooth positioning technology, and in particular to a Bluetooth fingerprint positioning method, device, equipment, storage medium and product. Background Art

[0002] Indoor Positioning System (IPS) relies on systems that use non-satellite alternative signal sources. For example, non-satellite alternative signal sources such as ultrasound, infrared, and radio signals (Wi-Fi, RFID, and Bluetooth LowEnergy (BLE)), each of which has its advantages and disadvantages and is sensitive to different types of noise. The benefits of IPS using BLE are its low power consumption, low network latency, and high sampling rate. However, IPS systems using BLE rely on received signal strength (RSSI), and in actual situations, object obstruction and signal fluctuations are very common, which can easily affect the received signal strength of BLE. Existing IPS systems using BLE use fingerprint positioning technology to improve the impact of object obstruction and signal fluctuations on the received signal strength of BLE.

[0003] Since the accuracy of fingerprint positioning technology depends on fingerprint collection and reference point selection, the current fingerprint collection generally adopts dynamic collection methods to reduce collection time and labor costs. However, since the collectors are in the process of moving, the collected signals contain signal information within a certain range of fixed fingerprint points and their surroundings. Averaging these signals to construct fingerprint maps will lead to inaccurate signal strength of fingerprint points, thereby increasing positioning errors. Summary of the invention

[0004] The present invention provides a Bluetooth fingerprint positioning method, device, equipment, storage medium and product, which improves the accuracy of fingerprint positioning by narrowing the sampling range of RSSI of a predetermined reference point, using RSSI data deviating from the reference point for training, and fine-tuning the reference point position.

[0005] In order to achieve the above object, an embodiment of the present invention provides a Bluetooth fingerprint positioning method, comprising:

[0006] Acquire reference point signal data of at least three target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points;

[0007] Constructing a fingerprint point of the target reference point in a fingerprint map according to the reference point signal data;

[0008] Performing positioning calculation on the reference point signal data and the adjacent point signal data to obtain the predicted position coordinates of the adjacent point;

[0009] According to the deviation between the predicted position coordinates and the actual position coordinates of the neighboring points, the position of the fingerprint point corresponding to the target reference point is fine-tuned in the fingerprint map to improve the fingerprint positioning accuracy of the target reference point.

[0010] As an improvement of the above solution, constructing the fingerprint point of the target reference point in the fingerprint map according to the reference point signal data includes:

[0011] Acquire all received Bluetooth nodes of the target reference point, and determine at least three target Bluetooth nodes of the target reference point;

[0012] Receiving Bluetooth signal data of the target Bluetooth node to obtain reference point signal data of the target reference point;

[0013] The reference point signal data is calculated to obtain a fingerprint map, and the fingerprint point of the target reference point is constructed in the fingerprint map.

[0014] As an improvement of the above solution, the performing positioning calculation on the reference point signal data and the neighboring point signal data to obtain the predicted position coordinates of the neighboring point includes:

[0015] generating a weighting parameter for each target reference point according to the similarity between the reference point signal data and the neighboring point signal data;

[0016] Performing weighted summation on the weighted parameters to obtain a weight matrix of the target reference point;

[0017] The predicted position coordinates of the neighboring points are calculated based on the weight matrix and the two-dimensional position coordinates of the target reference point.

[0018] As an improvement of the above solution, the position of the fingerprint point corresponding to the target reference point is fine-tuned in the fingerprint map according to the deviation between the predicted position coordinates and the actual position coordinates of the neighboring points to improve the fingerprint positioning accuracy of the target reference point, including:

[0019] According to the predicted position coordinates and the actual position coordinates of the neighboring points, the predicted position coordinates are iteratively updated using a Delta criterion to optimize the deviation between the predicted position coordinates and the actual position coordinates until convergence;

[0020] According to the optimized deviation, the position of the fingerprint point corresponding to the target reference point is fine-tuned in the fingerprint map to improve the fingerprint positioning accuracy of the target reference point.

[0021] As an improvement of the above solution, the weighted summing of the weighted parameters to obtain the weight matrix of the target reference point includes:

[0022] The KNN algorithm is used to perform weighted summation on the weighted parameters to obtain a weight matrix of the target reference point.

[0023] As an improvement of the above solution, the step of acquiring reference point signal data of at least three target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points includes:

[0024] A dynamic acquisition method is adopted to obtain reference point signal data of at least three target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points.

[0025] In order to achieve the above object, an embodiment of the present invention provides a Bluetooth fingerprint positioning device, comprising:

[0026] A signal data acquisition module, used to acquire reference point signal data of at least three target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points;

[0027] A fingerprint map construction module, used to construct a fingerprint point of the target reference point in a fingerprint map according to the reference point signal data;

[0028] A position coordinate calculation module, used to perform positioning calculation on the reference point signal data and the adjacent point signal data to obtain the predicted position coordinates of the adjacent point;

[0029] The fingerprint map adjustment module is used to fine-tune the position of the fingerprint point corresponding to the target reference point in the fingerprint map according to the deviation between the predicted position coordinates and the actual position coordinates of the neighboring points, so as to improve the fingerprint positioning accuracy of the target reference point.

[0030] In order to achieve the above-mentioned purpose, an embodiment of the present invention provides a Bluetooth fingerprint positioning device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the above-mentioned Bluetooth fingerprint positioning method when executing the computer program.

[0031] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned Bluetooth fingerprint positioning method.

[0032] To achieve the above objective, an embodiment of the present invention further provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the steps of the above Bluetooth fingerprint positioning method.

[0033] Compared with the prior art, the Bluetooth fingerprint positioning method, device, equipment, storage medium and product disclosed in the embodiment of the present invention obtain reference point signal data of at least three target reference points and neighboring point signal data of several neighboring points deviating from the target reference points; construct the fingerprint point of the target reference point in the fingerprint map according to the reference point signal data; perform positioning calculation on the reference point signal data and the neighboring point signal data to obtain the predicted position coordinates of the neighboring point; and fine-tune the position of the fingerprint point corresponding to the target reference point in the fingerprint map according to the deviation between the predicted position coordinates and the actual position coordinates of the neighboring point to improve the fingerprint positioning accuracy of the target reference point. By narrowing the sampling range of the RSSI of the predetermined reference point, the RSSI data deviating from the reference point is used for training, and the reference point position is fine-tuned to improve the accuracy of fingerprint positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flowchart of a Bluetooth fingerprint positioning method provided by an embodiment of the present invention;

[0035] Figure 2 is an architecture diagram of a single-layer neural network provided by an embodiment of the present invention;

[0036] Figure 3 is a schematic diagram of a structure of a reference point and its adjacent points provided by an embodiment of the present invention;

[0037] Figure 4 is a structural schematic diagram of a Bluetooth fingerprint positioning device provided by an embodiment of the present invention;

[0038] Figure 5 It is a structural block diagram of a Bluetooth fingerprint positioning device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] 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.

[0040] It should be noted that the terms "comprises" and "specifically" and any variations of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0041] See also Figure 1 , Figure 1 : is a flow chart of a Bluetooth fingerprint positioning method provided by an embodiment of the present invention, the Bluetooth fingerprint positioning method comprising:

[0042] S1, acquiring reference point signal data of at least three target reference points and neighboring point signal data of a plurality of neighboring points deviating from the target reference points;

[0043] S2, constructing a fingerprint point of the target reference point in a fingerprint map according to the reference point signal data;

[0044] S3, performing positioning calculation on the reference point signal data and the neighboring point signal data to obtain the predicted position coordinates of the neighboring point;

[0045] S4, fine-tuning the position of the fingerprint point corresponding to the target reference point in the fingerprint map according to the deviation between the predicted position coordinates and the actual position coordinates of the neighboring points, so as to improve the fingerprint positioning accuracy of the target reference point.

[0046] Exemplarily, the Bluetooth fingerprint positioning method can be implemented by a Bluetooth positioning server, and the Bluetooth fingerprint positioning method described in the embodiment of the present invention can be applied to indoor positioning. The Bluetooth positioning server can exchange information with the user. The Bluetooth positioning server obtains all Bluetooth nodes in the target area that can receive Bluetooth signal data, and determines the target reference point of fingerprint positioning within the target area and the neighboring points of the target reference point based on these Bluetooth nodes. These neighboring points can be several points on a circle with a radius of a certain distance δ centered on the target reference point, or several points on the sides of a square formed by extending a distance δ up, down, left and right with the target reference point as the center. The embodiment of the present invention does not limit the selection of neighboring points. It can be understood that these neighboring points are used to fine-tune the position of the target reference point to improve the fingerprint positioning accuracy of the target reference point. The distance δ between the neighboring point and the target reference point and the number of neighboring points can be set as needed. The Bluetooth positioning server receives reference point signal data of a target reference point and neighboring point signal data of neighboring points, and constructs a fingerprint point of the target reference point in a fingerprint map according to the reference point signal data; inputs the reference point signal data and the neighboring point signal data into a Bluetooth positioning model to obtain predicted position coordinates of the neighboring points; adjusts the predicted position coordinates of the neighboring points according to corresponding deviations between the predicted position coordinates and the actual position coordinates of each neighboring point until convergence (the deviation is less than a preset threshold, which is set as needed); and fine-tunes the position of the fingerprint point corresponding to the target reference point in the fingerprint map according to the adjusted predicted position coordinates to improve the fingerprint positioning accuracy of the target reference point.

[0047] Specifically, the step S2 includes:

[0048] S21, acquiring all received Bluetooth nodes of the target reference point, and determining at least three target Bluetooth nodes of the target reference point;

[0049] S22, receiving Bluetooth signal data of the target Bluetooth node, and obtaining reference point signal data of the target reference point;

[0050] S23, calculating the reference point signal data to obtain a fingerprint map, and constructing the fingerprint point of the target reference point in the fingerprint map.

[0051] For example, several target reference points are determined in the fingerprint area corresponding to the target area and marked as RP (Reference Point). Assume that there are N RPs in the entire fingerprint area, and there are L Bluetooth nodes (BLE) that can be received by all target reference points. The coordinates of RP in two-dimensional space are marked as:

[0052]

[0053] Where R is the set of two-dimensional position coordinates of the target reference point RP, x 1 and 1 is the horizontal and vertical coordinates of the first target reference point RP, x N and N are the horizontal and vertical coordinates of the Nth target reference point RP, and T is the matrix transposition identifier.

[0054] In the offline collection phase, at least three target Bluetooth nodes are determined for each target reference point to receive Bluetooth signal data. The Bluetooth signal data from the same Bluetooth node will be received multiple times in the RP and a small range close to the RP. The average value of the Bluetooth signal data received from the target Bluetooth node is used as the reference point signal data of the target reference point RP. The set of original RSSI values ​​received from the jth BLE at the i-th RP is Ψ i,j It is expressed as:

[0055] Ψ i,j ={ψ i,j (τ); 1≤τ≤q}

[0056] Where q represents the number of Bluetooth signal data received from the jth BLE at the i-th RP, ψ i,j (τ) represents the Bluetooth signal data (raw RSSI value) received from the jth BLE at the i-th RP at time τ.

[0057] After the Bluetooth node screening is performed, a fingerprint map Θ can be constructed by calculating the original RSSI values ​​of all RP points, which is expressed in matrix form as follows:

[0058]

[0059] Among them, θ N,L represents the average signal strength (average RSSI value) of the Lth Bluetooth node received by the Nth RP at multiple times, θ 1,2 It represents the average signal strength of the second Bluetooth node received at the first RP at multiple times. It is known that the i-th RP receives a total of q signals from the j-th Bluetooth node, and the signal strength received at time τ is ψ i,j (τ), then the average signal strength θ of the jth Bluetooth node received at the i-th RP at multiple times i,j The calculation method is as follows:

[0060]

[0061] In the positioning calculation stage, the RSSI value is represented by vector V as:

[0062] V=[v 1 v 2 ···v L ]

[0063] Among them, v 1 is the RSSI value received from the first Bluetooth node, v L is the RSSI value received from the Lth Bluetooth node.

[0064] Construct the fingerprint point of the target reference point in the fingerprint map. For example, in an embodiment of the present invention, a Bluetooth positioning model is pre-trained. The Bluetooth positioning model is pre-trained based on big data. The Bluetooth positioning model can be a convolutional neural network. After inputting the signal data of each reference point into the Bluetooth positioning model, the Bluetooth signal strength feature can be selected from the reference point signal data, so as to select the fingerprint point of the target reference point from the fingerprint map according to the Bluetooth signal strength feature. The Bluetooth positioning model will automatically output the fingerprint point of the target reference point.

[0065] Specifically, the step S3 includes:

[0066] S31, generating a weighting parameter for each target reference point according to the similarity between the reference point signal data and the neighboring point signal data;

[0067] S32, performing weighted summation on the weighted parameters to obtain a weight matrix of the target reference point;

[0068] S33, calculating the predicted position coordinates of the neighboring points according to the weight matrix and the two-dimensional position coordinates of the target reference point.

[0069] For example, during the positioning process, the RSSI of the TP is used as the positioning input and matched with the RP to calculate the estimated position of the TP. A weighting parameter is assigned to each RP according to the similarity between the RSSI of each RP and the original signal strength received at the TP point. The weighting parameter is expressed in a vector as follows:

[0070] Ω=[ω 1 ω 2 ···ω N ]

[0071] Among them, ω 1 is the weight of the first RP, ω N is the weight of the Nth RP.

[0072] The more direct inverse of the Minkowski distance is used as a method to calculate the RP weight.

[0073]

[0074] Among them, ω i is the weight of the ith RP, v j is the Bluetooth signal strength (RSSI value) of the jth target Bluetooth node received in the test data. This is a generalized distance calculation method. When Manhattan distance is used, p=1, and when Euclidean distance is used, p=2.

[0075] Before doing the weighted summation, the weight vector must be normalized to obtain the normalized weight vector Ω′, which is calculated as follows:

[0076]

[0077] Ω′=[ω′ 1 ω′ 2 ···ω′ N ]

[0078] Among them, ω′ i is the normalized weight of the ith RP, ω′ 1 is the normalized weight of the first RP, ω′ N is the normalized weight of the Nth RP.

[0079] Use the KNN algorithm, that is, select k RPs with the largest weights for weighted summation, and other RPs with lower weights will be ignored. The KNN matrix is ​​defined as follows:

[0080]

[0081] Among them, λ iIt can only take the value 0 or 1, i = 1, 2, ..., N. When the i-th RP is selected, λ i =1; otherwise, λ i = 0. A total of N′ RPs are selected, then Λ should meet the following conditions:

[0082]

[0083] The weight matrix after KNN screening is Ω″:

[0084] Ω″=Ω′Λ

[0085] Finally, the predicted position coordinates of the neighboring points are expressed by the vector U = [u x u y ] indicates that T is calculated as:

[0086] U=Ω″R+E

[0087] Where E = [∈ x ∈ y ], represents the deviation caused by noise, in the unknown case, ∈ x ,∈ y If set to 0, E will be updated repeatedly in the neural network during the reference point fine-tuning step.

[0088] Specifically, the step S4 includes:

[0089] S41, according to the predicted position coordinates and the actual position coordinates of the neighboring points, adopting the Delta criterion to iteratively update the predicted position coordinates, and optimizing the deviation between the predicted position coordinates and the actual position coordinates until convergence;

[0090] S42, fine-tuning the position of the fingerprint point corresponding to the target reference point in the fingerprint map according to the optimized deviation, so as to improve the fingerprint positioning accuracy of the target reference point.

[0091] For example, the coordinates of the reference points are updated based on the weight matrix Ω″. The reference point fine-tuning uses a single-layer neural network. The single-layer network maintains the weighted sum structure by applying a linear activation function. Although it is simple, it performs well on many fingerprint-based algorithms. The architecture of the single-layer network is as follows Figure 2 As shown, Figure 2It is an architecture diagram of a single-layer neural network provided by an embodiment of the present invention. It is worth noting that the neural network stores information in the form of weights, and the systematic method of modifying the weights according to the given information is called the learning rule. Since training is the only way for neural networks to systematically store information, learning rules are an important component in neural network research. In the reference point fine-tuning, the training group in TP is used as a fixed training data set. The position is first estimated by RP weighting and KNN, and then the reference point coordinates and the estimated error are continuously updated to minimize the positioning error following the Delta criterion.

[0092] The Delta criterion is a heuristic method that aims to solve the problem of parameter adjustment of multi-layer perceptrons. It uses the gradient descent method to find the extreme value and make the target converge to the best approximate value. The core idea of ​​this method is to use the gradient descent algorithm to optimize the objective function. By continuously iteratively adjusting the parameters, the objective function reaches the minimum or maximum value, thereby achieving the optimization goal. The Delta criterion is not only applicable to real-valued functions of single variables, but also to functions of multi-dimensional variables. By calculating the gradient of the function, the direction and step size of each iteration are determined, and the optimal solution is gradually approached. In the case of multiple dimensions, the gradient is a vector field that points to the direction in which the function value changes fastest. By adjusting the parameters along this direction, it can converge to the optimal solution faster.

[0093] Specifically, define R (t) ,E (t) ,U (t) are the RP coordinate matrix, unknown deviation vector and predicted position coordinate vector at the tth iteration respectively. (t) The initial value is R (0) =R,E (t) The initial value is E (0) =E, assuming that the real position of TP is marked as G = [g x g y ], according to the gradient in RP space, R can be calculated using the following equation (t+1) ,E (t+1) ,U (t) Values:

[0094] R (t+1) =R (t) +αΩ″(GU (t) )

[0095] E (t+1) =E (t) +αΩ″(GU (t) )

[0096] U (t) =Ω″R (t) +E (t)

[0097] The learning rule is obtained from the partial derivative of the loss function for each RP, where the loss function is the mean square error (MSE). The constant α represents the proportional constant, called the learning rate, and the empirical value α=0.0001 is selected. It should be noted that the Delta rule is only valid when ω′ i ≠ 0, which means that only the RP with the largest weight selected by KNN will be updated. This also ensures that some RPs that are unlikely to be relevant to the current estimate will not be updated unnecessarily.

[0098] More specifically, the step S32 includes:

[0099] The KNN algorithm is used to perform weighted summation on the weighted parameters to obtain a weight matrix of the target reference point.

[0100] Specifically, the S1 includes:

[0101] A dynamic acquisition method is adopted to obtain reference point signal data of at least three target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points.

[0102] It is worth noting that several neighboring points deviating from the target reference point used for fingerprint fine-tuning are marked as TP. For each RP, an embodiment of the present invention sets several TPs around it. Taking the setting of 4 TPs as an example, assuming that the coordinates of the RP are (x, y), the coordinates of the 4 TPs are (x+δ, y+δ)(x-δ, y+δ)(x+δ, y-δ)(x-δ, y-δ), and the value of δ is determined by the area of ​​the fingerprint region and the RP spacing, and generally one quarter of the RP spacing is selected. The TP is further divided into two independent data sets: a training data set for training the reference point fine-tuning model and a test data set for testing the positioning effect after fine-tuning. The data size ratio between the training and test data sets can be set to 3:1. If Figure 3 As shown, Figure 3 is a structural schematic diagram of a reference point and its neighboring points provided by an embodiment of the present invention, wherein the square point represents the RP, the circular point represents the training group in the TP, and the cross point represents the test group in the TP.

[0103] The embodiment of the present invention discloses a Bluetooth fingerprint positioning method, which obtains reference point signal data of at least three target reference points and neighboring point signal data of several neighboring points deviating from the target reference points; constructs the fingerprint point of the target reference point in a fingerprint map according to the reference point signal data; performs positioning calculation on the reference point signal data and the neighboring point signal data to obtain the predicted position coordinates of the neighboring point; and fine-tunes the position of the fingerprint point corresponding to the target reference point in the fingerprint map according to the deviation between the predicted position coordinates and the actual position coordinates of the neighboring point to improve the fingerprint positioning accuracy of the target reference point. By narrowing the sampling range of the RSSI of the predetermined reference point, the RSSI data deviating from the reference point is used for training, and the reference point position is fine-tuned to improve the accuracy of fingerprint positioning.

[0104] See also Figure 4 , Figure 4 1 is a schematic diagram of the structure of a Bluetooth fingerprint positioning device 10 provided in an embodiment of the present invention. The Bluetooth fingerprint positioning device 10 includes:

[0105] A signal data acquisition module 11 is used to acquire reference point signal data of at least three target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points;

[0106] A fingerprint map construction module 12, configured to construct a fingerprint point of the target reference point in a fingerprint map according to the reference point signal data;

[0107] A position coordinate calculation module 13 is used to perform positioning calculation on the reference point signal data and the adjacent point signal data to obtain the predicted position coordinates of the adjacent point;

[0108] The fingerprint map adjustment module 14 is used to fine-tune the position of the fingerprint point corresponding to the target reference point in the fingerprint map according to the deviation between the predicted position coordinates and the actual position coordinates of the neighboring points, so as to improve the fingerprint positioning accuracy of the target reference point.

[0109] Specifically, the fingerprint map construction module 12 is used to:

[0110] Acquire all received Bluetooth nodes of the target reference point, and determine at least three target Bluetooth nodes of the target reference point;

[0111] Receiving Bluetooth signal data of the target Bluetooth node to obtain reference point signal data of the target reference point;

[0112] The reference point signal data is calculated to obtain a fingerprint map, and the fingerprint point of the target reference point is constructed in the fingerprint map.

[0113] Specifically, the position coordinate calculation module 13 is used to:

[0114] generating a weighting parameter for each target reference point according to the similarity between the reference point signal data and the neighboring point signal data;

[0115] Performing weighted summation on the weighted parameters to obtain a weight matrix of the target reference point;

[0116] The predicted position coordinates of the neighboring points are calculated based on the weight matrix and the two-dimensional position coordinates of the target reference point.

[0117] Specifically, the fingerprint map adjustment module 14 is used to:

[0118] According to the predicted position coordinates and the actual position coordinates of the neighboring points, the predicted position coordinates are iteratively updated using a Delta criterion to optimize the deviation between the predicted position coordinates and the actual position coordinates until convergence;

[0119] According to the optimized deviation, the position of the fingerprint point corresponding to the target reference point is fine-tuned in the fingerprint map to improve the fingerprint positioning accuracy of the target reference point.

[0120] More specifically, the weighted summing of the weighted parameters to obtain the weight matrix of the target reference point includes:

[0121] The KNN algorithm is used to perform weighted summation on the weighted parameters to obtain a weight matrix of the target reference point.

[0122] Specifically, the signal data acquisition module 11 is used to:

[0123] A dynamic acquisition method is adopted to obtain reference point signal data of at least three target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points.

[0124] A Bluetooth fingerprint positioning device 10 provided in an embodiment of the present invention can implement all the processes of the Bluetooth fingerprint positioning method of the above embodiment. The functions of each module in the device and the technical effects achieved are respectively the same as the functions and technical effects achieved by the Bluetooth fingerprint positioning method of the above embodiment, and will not be repeated here.

[0125] See also Figure 5 , Figure 5: is a structural diagram of a Bluetooth fingerprint positioning device 20 provided in an embodiment of the present invention. The Bluetooth fingerprint positioning device 20 of this embodiment includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned Bluetooth fingerprint positioning method embodiment are implemented. Alternatively, when the processor 21 executes the computer program, the functions of each module in the above-mentioned Bluetooth fingerprint positioning device embodiment are implemented.

[0126] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the Bluetooth fingerprint positioning device 20.

[0127] The Bluetooth fingerprint positioning device 20 can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The Bluetooth fingerprint positioning device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is only an example of the Bluetooth fingerprint positioning device 20 and does not constitute a limitation on the Bluetooth fingerprint positioning device 20. It may include more or less components than shown in the figure, or combine certain components, or different components. For example, the Bluetooth fingerprint positioning device 20 may also include input and output devices, network access devices, buses, etc.

[0128] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the Bluetooth fingerprint positioning device 20, and uses various interfaces and lines to connect various parts of the entire Bluetooth fingerprint positioning device 20.

[0129] The memory 22 can be used to store the computer program and / or module. The processor 21 realizes various functions of the Bluetooth fingerprint positioning device 20 by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0130] Wherein, if the module integrated in the Bluetooth fingerprint positioning device 20 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 such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 21, the steps of the above-mentioned method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0131] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0132] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the Bluetooth fingerprint positioning method as described in the above embodiment.

[0133] In addition, an embodiment of the present invention further provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the steps of the Bluetooth fingerprint positioning method of the above embodiment.

[0134] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A Bluetooth fingerprint positioning method, characterized in that: include: Acquire reference point signal data of at least three target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points; Constructing a fingerprint point of the target reference point in a fingerprint map according to the reference point signal data; Performing positioning calculation on the reference point signal data and the adjacent point signal data to obtain the predicted position coordinates of the adjacent point; According to the deviation between the predicted position coordinates and the actual position coordinates of the neighboring points, the position of the fingerprint point corresponding to the target reference point is fine-tuned in the fingerprint map to improve the fingerprint positioning accuracy of the target reference point.

2. The Bluetooth fingerprint positioning method according to claim 1, characterized in that: The step of constructing the fingerprint point of the target reference point in the fingerprint map according to the reference point signal data includes: Acquire all received Bluetooth nodes of the target reference point, and determine at least three target Bluetooth nodes of the target reference point; Receiving Bluetooth signal data of the target Bluetooth node to obtain reference point signal data of the target reference point; The reference point signal data is calculated to obtain a fingerprint map, and the fingerprint point of the target reference point is constructed in the fingerprint map.

3. The Bluetooth fingerprint positioning method according to claim 1, characterized in that: The performing positioning calculation on the reference point signal data and the neighboring point signal data to obtain the predicted position coordinates of the neighboring point includes: generating a weighting parameter for each target reference point according to the similarity between the reference point signal data and the neighboring point signal data; Performing weighted summation on the weighted parameters to obtain a weight matrix of the target reference point; The predicted position coordinates of the neighboring points are calculated based on the weight matrix and the two-dimensional position coordinates of the target reference point.

4. The Bluetooth fingerprint positioning method according to claim 1, characterized in that: The step of fine-tuning the position of the fingerprint point corresponding to the target reference point in the fingerprint map according to the deviation between the predicted position coordinates and the actual position coordinates of the neighboring points to improve the fingerprint positioning accuracy of the target reference point includes: According to the predicted position coordinates and the actual position coordinates of the neighboring points, the predicted position coordinates are iteratively updated using a Delta criterion to optimize the deviation between the predicted position coordinates and the actual position coordinates until convergence; According to the optimized deviation, the position of the fingerprint point corresponding to the target reference point is fine-tuned in the fingerprint map to improve the fingerprint positioning accuracy of the target reference point.

5. The Bluetooth fingerprint positioning method according to claim 3, characterized in that: The step of performing weighted summation on the weighted parameters to obtain a weight matrix of the target reference point includes: The KNN algorithm is used to perform weighted summation on the weighted parameters to obtain a weight matrix of the target reference point.

6. The Bluetooth fingerprint positioning method according to claim 1, characterized in that: The acquiring of reference point signal data of at least three target reference points and neighboring point signal data of a plurality of neighboring points deviating from the target reference points comprises: A dynamic acquisition method is adopted to obtain reference point signal data of at least three target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points.

7. A Bluetooth fingerprint positioning device, characterized in that: include: A signal data acquisition module, used to acquire reference point signal data of at least three target reference points and adjacent point signal data of a plurality of adjacent points deviating from the target reference points; A fingerprint map construction module, used to construct a fingerprint point of the target reference point in a fingerprint map according to the reference point signal data; A position coordinate calculation module, used to perform positioning calculation on the reference point signal data and the adjacent point signal data to obtain the predicted position coordinates of the adjacent point; The fingerprint map adjustment module is used to fine-tune the position of the fingerprint point corresponding to the target reference point in the fingerprint map according to the deviation between the predicted position coordinates and the actual position coordinates of the neighboring points, so as to improve the fingerprint positioning accuracy of the target reference point.

8. A Bluetooth fingerprint positioning device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the Bluetooth fingerprint positioning method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the Bluetooth fingerprint positioning method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product is stored in a storage medium, and the program product is executed by at least one processor to implement the steps of the Bluetooth fingerprint positioning method as described in any one of claims 1 to 6.

Images