Bluetooth indoor positioning method and device

Abstract

The present invention provides a Bluetooth indoor positioning method and device, the method comprising: obtaining the distance between the terminal to be positioned and each first Bluetooth beacon based on the RSSI of Bluetooth signals sent by multiple indoor first Bluetooth beacons received by the terminal to be positioned based on a signal attenuation model; obtaining the initial position of the terminal to be positioned based on the distance between the terminal to be positioned and each first Bluetooth beacon based on a geometric method, and determining the area where the terminal to be positioned is located according to the initial position; determining the final position of the terminal to be positioned according to the RSSI of Bluetooth signals sent by multiple indoor second Bluetooth beacons received by sample terminals at each preset position in the area and the RSSI of Bluetooth signals sent by multiple first Bluetooth beacons received by the terminal to be positioned. The present invention improves the accuracy and stability of indoor positioning results.

Description

Technical Field

[0001] The present invention relates to the field of wireless positioning technology, and in particular to a Bluetooth indoor positioning method and device. Background Art

[0002] With the popularization of mobile Internet, various indoor positioning technologies have received more attention and development, such as Bluetooth positioning, RFID (Radio Frequency Identification) positioning, WIFI (Wireless Fidelity) positioning, UWB (Ultra Wide Band) positioning and ultrasonic positioning, etc. Among them, Bluetooth positioning technology is widely used in various fields due to its advantages such as low equipment cost, relatively high positioning accuracy and low power consumption.

[0003] At present, Bluetooth indoor positioning technology is mainly divided into two categories: measurement-based and location fingerprint-based. Among them, measurement-based Bluetooth indoor positioning extracts parameter information from the received Bluetooth signal, calculates the absolute distance between the target terminal and the Bluetooth beacon based on the parameters, and then uses geometric methods to locate the actual coordinates of the target terminal. The current mainstream measurement parameters include RSSI (Received Signal Strength Indication), AOA (Angle Of Arrival), TOA (Time Of Arrival) and TDOA (Time Difference Of Arrival). Commonly used geometric methods include trilateral positioning, triangulation positioning and triangulation centroid positioning.

[0004] Bluetooth indoor positioning based on location fingerprint is divided into two stages. The first is the offline stage, in which Bluetooth signals are collected at various locations in the indoor environment and features are extracted from them as the fingerprint of the location. The simplest and most commonly used feature is the RSSI sequence; then the online positioning stage, the classification algorithm is used to match the received Bluetooth signal with the fingerprint of each location to obtain the positioning result. Commonly used classification algorithms include KNN (K-NearestNeighbor), SVM (Support Vector Machine), decision tree and neural network.

[0005] Since Bluetooth signal propagation is easily affected by the environment, even at the same location, the measured Bluetooth signal parameter information is always fluctuating, which poses a challenge to the accuracy of Bluetooth positioning. Among them, measurement-based indoor positioning is more susceptible to environmental noise interference due to its strong reliance on the accuracy of measurement data. When the observed value is RSSI, the path loss of indoor Bluetooth signals follows the logarithmic distance loss model, and the formula is as follows:

[0006]

[0007] Among them, P L (d) represents the path loss when the distance between the transceiver devices is d, in dB, n represents the path loss exponent, X σ represents the ambient noise, and d0 represents the reference position.

[0008] But in fact, the influence of environmental factors on signal propagation makes there is no stable relationship between signal attenuation and actual distance. Therefore, when calculating distance based on RSSI, the error is large.

[0009] When the observed quantities are AOA, TOA and TDOA, unlike in an open outdoor environment, Bluetooth signals in indoor environments have serious non-linear propagation conditions such as reflection, diffraction and so on. In addition, the propagation time of the signal on each path is very close. The resolution of ordinary commercial equipment, such as mobile phones, is not enough to distinguish the signals that are so close in time and angle, and additional equipment such as antenna arrays need to be installed. Therefore, on ordinary equipment, the positioning results based on signal angle and signal arrival time are not accurate enough. These factors also limit the promotion of indoor positioning methods based on measurement.

[0010] The two stages of the indoor positioning method based on location fingerprint also rely on data collection. Although the dependence on measurement data is weakened, additional factors such as fingerprint feature extraction and classifier selection are added. In addition, the accuracy of the positioning result strongly depends on the extraction of fingerprint features and the selection of the subsequent classifier. In real-life scenarios, the generalization performance of a classifier is usually limited, that is, different data measured at the same location may obtain different classification results after passing through the classifier, thereby reducing the accuracy of positioning. Summary of the invention

[0011] The present invention provides a Bluetooth indoor positioning method and device, which are used to solve the defect of inaccurate Bluetooth indoor positioning in the prior art and improve the accuracy of Bluetooth indoor positioning.

[0012] The present invention provides a Bluetooth indoor positioning method, comprising:

[0013] Based on the signal attenuation model, according to the RSSI of the Bluetooth signals sent by the multiple first indoor Bluetooth beacons received by the terminal to be located, the distance between the terminal to be located and each first Bluetooth beacon is obtained;

[0014] Acquire the initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon based on a geometric method, and determine the area where the terminal to be located is located according to the initial position;

[0015] The final position of the terminal to be located is determined according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons indoors and received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons and received by the terminal to be located.

[0016] According to a Bluetooth indoor positioning method provided by the present invention, the final position of the terminal to be located is determined according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons indoors and received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located, including:

[0017] Training the AdaBoost binary classifier according to the RSSI of the Bluetooth signals sent by the plurality of second Bluetooth beacons indoors and received by the sample terminals at the preset positions in the area, and obtaining the trained AdaBoost binary classifier corresponding to each preset position;

[0018] Inputting the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located into the trained AdaBoost binary classifier corresponding to each preset position in the area, and outputting the probability that the terminal to be located is located at each preset position;

[0019] The final position of the terminal to be located is obtained by multiplying the probability that the terminal to be located is located at each preset position by the coordinates of each preset position and then adding them.

[0020] According to a Bluetooth indoor positioning method provided by the present invention, the AdaBoost binary classifier is trained according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons indoors and received by the sample terminals at each preset position in the area, and the trained AdaBoost binary classifier corresponding to each preset position is obtained, including:

[0021] Calculate the RSSI average value of the Bluetooth signal sent by each second Bluetooth beacon received by the sample terminal at any preset position at multiple times, and use the second Bluetooth beacon corresponding to the largest preset number of RSSI average values ​​as the target beacon;

[0022] The rssi of all the Bluetooth signals sent by the target beacons received by the sample terminal at the preset position at each moment is taken as a positive sample, and the rssi of all the Bluetooth signals sent by the target beacons received by the sample terminals at other preset positions in the room except the preset position at each moment is taken as a negative sample, and the AdaBoost binary classifier is trained to obtain the trained AdaBoost binary classifier corresponding to the preset position.

[0023] According to a Bluetooth indoor positioning method provided by the present invention, before taking the RSSI of the Bluetooth signals sent by all the target beacons received by the sample terminals at other preset positions in the room except the preset position at each moment as negative samples, the method further includes:

[0024] Calculate a first ratio of the number of target beacons whose Bluetooth signals are not received by the sample terminals at the other preset positions to the total number of the target beacons;

[0025] When the first ratio is less than or equal to the first preset threshold and greater than 0, the RSSI corresponding to the target beacon whose Bluetooth signal is not received by the sample terminal at the other preset position is set to the first preset value;

[0026] When the first ratio is greater than the first preset threshold, the RSSI corresponding to the other preset positions is not taken as a negative sample.

[0027] According to a Bluetooth indoor positioning method provided by the present invention, the calculation of the RSSI average value of the Bluetooth signal sent by each second Bluetooth beacon received by a sample terminal at any preset position at multiple times includes:

[0028] Combining the RSSIs of the Bluetooth signals sent by the second Bluetooth beacons received by the sample terminal at each preset position at multiple times into the same sequence;

[0029] Align the rssi in each sequence according to the timestamp of the bluetooth signal to which the rssi belongs;

[0030] If the rssi corresponding to any timestamp in the aligned sequence is empty, fill the rssi corresponding to the timestamp with a second preset value;

[0031] In a case where a second ratio of the RSSIs in the padded sequence that are less than the second preset threshold to the total number of RSSIs in the sequence is greater than a third preset threshold, deleting the sequence;

[0032] Calculate the average rssi value in each retained sequence.

[0033] According to a Bluetooth indoor positioning method provided by the present invention, the method of obtaining the distance between the terminal to be positioned and each first Bluetooth beacon based on the RSSI of the Bluetooth signals sent by multiple first indoor Bluetooth beacons received by the terminal to be positioned based on the signal attenuation model includes:

[0034] According to the RSSI of the Bluetooth signal sent by each second Bluetooth coordinate received by the sample terminal at each preset position in the room, the parameters in the signal attenuation model are fitted to obtain the parameters in the signal attenuation model;

[0035] Constructing a signal attenuation model corresponding to each second Bluetooth beacon according to the parameters in the signal attenuation model;

[0036] In the case that the first Bluetooth beacon exists in the second Bluetooth beacon, the distance between the terminal to be located and the first Bluetooth beacon is obtained according to the RSSI of the Bluetooth signal sent by the first Bluetooth beacon based on the signal attenuation model corresponding to the first Bluetooth beacon.

[0037] According to a Bluetooth indoor positioning method provided by the present invention, the method of obtaining the distance between the terminal to be positioned and each first Bluetooth beacon based on the RSSI of the Bluetooth signals sent by multiple first indoor Bluetooth beacons received by the terminal to be positioned based on the signal attenuation model includes:

[0038] Selecting the three largest RSSIs from the RSSIs of the Bluetooth signals sent by the plurality of first Bluetooth beacons;

[0039] Input each of the three largest RSSIs into the signal attenuation model corresponding to the first Bluetooth beacon to which each RSSI belongs, and output the distance between the first Bluetooth beacon to which each RSSI belongs and the terminal to be located;

[0040] Accordingly, the obtaining the initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon based on the geometric method includes:

[0041] The initial position of the terminal to be located is acquired according to the distance between the terminal to be located and each first Bluetooth beacon based on the three-side positioning method.

[0042] The present invention also provides a Bluetooth indoor positioning device, comprising:

[0043] An acquisition module, configured to acquire the distance between the terminal to be located and each first Bluetooth beacon based on the RSSI of the Bluetooth signals sent by the multiple first indoor Bluetooth beacons received by the terminal to be located based on a signal attenuation model;

[0044] A determination module, configured to obtain an initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon based on a geometric method, and determine an area where the terminal to be located is located according to the initial position;

[0045] The positioning module is used to determine the final position of the terminal to be located based on the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons indoors and received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located.

[0046] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned Bluetooth indoor positioning methods are implemented.

[0047] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned Bluetooth indoor positioning methods are implemented.

[0048] The Bluetooth indoor positioning and device provided by the present invention first uses a measurement-based Bluetooth indoor positioning method to determine the area where the terminal to be located is located, and then uses a location fingerprint-based indoor positioning method to calculate the position of the terminal to be located according to the RSSI collected at a preset position in the area and the RSSI of the Bluetooth signal received by the terminal to be located. By combining the two positioning methods, the advantages of the two methods are complemented, thereby improving the accuracy and stability of the indoor positioning results. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 This is one of the flow charts of the Bluetooth indoor positioning method provided by the present invention;

[0051] Figure 2 It is a schematic diagram of the training process of the AdaBoost binary classifier in the Bluetooth indoor positioning method provided by the present invention;

[0052] Figure 3 It is a schematic diagram of the parameter fitting process of the signal attenuation model in the Bluetooth indoor positioning method provided by the present invention;

[0053] Figure 4This is the second flow chart of the Bluetooth indoor positioning method provided by the present invention;

[0054] Figure 5 It is a structural schematic diagram of the Bluetooth indoor positioning device provided by the present invention;

[0055] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0057] Combine the following Figure 1 The Bluetooth indoor positioning method of the present invention is described, and the method comprises: step 101, based on the signal attenuation model, according to the RSSI of the Bluetooth signals sent by multiple indoor first Bluetooth beacons received by the terminal to be positioned, the distance between the terminal to be positioned and each first Bluetooth beacon is obtained;

[0058] In the online positioning stage, the data broadcast by each first Bluetooth beacon is collected in real time, and the data every 1s constitutes the test data set.

[0059] Extract the three key fields of major, minor and rssi from the test data set. Take major and minor as the identifier of the first Bluetooth beacon, and then perform Kalman filtering to reduce the impact of environmental noise and obtain a valid test data set.

[0060] Since Bluetooth signals are easily affected by environmental factors, the error will be large when calculating the distance based on the signal strength RSSI. In this embodiment, only the initial position of the terminal to be located determined based on RSSI is used as an intermediate result. Then, the approximate area where the terminal to be located is located is determined based on the initial position. Then, the exact location of the target user is determined based on the RSSI fingerprints at each preset position in the area and the RSSI of the terminal to be located.

[0061] The formula of the signal attenuation model is RSSI(d)=A+10ηlg(d). A and η are unknown parameters and can be obtained by data fitting. The RSSI of the Bluetooth signal sent by each first Bluetooth beacon received by the terminal to be located is used as the input of the signal attenuation model, that is, RSSI(d), and the distance d between the terminal to be located and each first Bluetooth beacon is obtained.

[0062] Step 102, obtaining the initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon based on a geometric method, and determining the area where the terminal to be located is located according to the initial position;

[0063] Among them, the geometric methods include three-side positioning, triangulation positioning and triangulation centroid positioning, and this embodiment is not limited to the types of geometric methods.

[0064] Since the position of each first Bluetooth beacon is known and the distance between the terminal to be located and each first Bluetooth beacon is known, the position (x, y) of the terminal to be located can be determined based on a geometric method and the determined position is used as the initial position.

[0065] Since the Bluetooth signal fluctuates greatly, there is a large deviation between the calculated result (x, y) and the actual position. The area where the terminal to be located is located is determined based on (x, y).

[0066] Optionally, a circular area with (x, y) as the origin and a radius of a preset value, such as 5 m, is used as the area where the terminal to be located is located.

[0067] Step 103, determining the final position of the terminal to be located according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons indoors and received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located.

[0068] Optionally, the fingerprint at each preset position is extracted according to the RSSI of the Bluetooth signal sent by the multiple second Bluetooth beacons in the room received by the sample terminal at each preset position in the area. The fingerprint of the terminal to be located is determined according to the RSSI of the Bluetooth signal sent by the multiple first Bluetooth beacons received by the terminal to be located. The fingerprint of the terminal to be located is compared with the fingerprints at each preset position to determine the final position of the terminal to be located.

[0069] In this embodiment, after first using a measurement-based Bluetooth indoor positioning method to determine the area where the terminal to be located is located, the indoor positioning method based on location fingerprint calculates the position of the terminal to be located according to the RSSI collected at a preset position in the area and the RSSI of the Bluetooth signal received by the terminal to be located. By combining the two positioning methods, the advantages of the two methods are complemented, thereby improving the accuracy and stability of the indoor positioning results.

[0070] On the basis of the above embodiments, the method of determining the final position of the terminal to be located according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons indoors and received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located in the present embodiment includes: training an AdaBoost binary classifier according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons indoors and received by the sample terminals at each preset position in the area, and obtaining a trained AdaBoost binary classifier corresponding to each preset position;

[0071] The AdaBoost algorithm is mostly used in the field of image recognition. This embodiment applies the AdaBoost algorithm to the field of Bluetooth indoor positioning. AdaBoost is an iterative algorithm that trains the same training set through multiple cycles of iteration to obtain multiple learning models, and then combines these models into a strong classifier. Compared with the traditional Bluetooth indoor positioning algorithm based on location fingerprint, which selects a single classifier such as SVM and neural network, the AdaBoost algorithm increases the generalization ability of the location fingerprint algorithm and can better adapt to Bluetooth signals with greater volatility.

[0072] There are two ways to implement multi-classification in AdaBoost. One is to directly implement multi-classification at one time by modifying the calculation method of weak classifier weights and sample weights. This method seems simple, but the amount of calculation is too large and the optimization process is complicated. Another idea is to decompose the multi-classification problem into a series of binary classification problems, that is, to train multiple binary classifiers.

[0073] This embodiment adopts the second idea, using training data to train each preset position separately to obtain an AdaBoost binary classifier set, reducing the complexity of model training. Although there are many classifiers, in actual positioning, only a few AdaBoost classifiers corresponding to the preset positions in the area where the terminal to be positioned is located will be used, so the real-time performance of positioning will not be greatly affected.

[0074] Inputting the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located into the trained AdaBoost binary classifier corresponding to each preset position in the area, and outputting the probability that the terminal to be located is located at each preset position;

[0075] The RSSI of the Bluetooth signal currently received by the terminal to be located is input into the AdaBoost binary classifier corresponding to each preset position in the area where the terminal to be located is located, and the probability that the terminal to be located is located at each preset position is output.

[0076] The final position of the terminal to be located is obtained by multiplying the probability that the terminal to be located is located at each preset position by the coordinates of each preset position and then adding them.

[0077] Optionally, the probability that the terminal to be located is located at each preset position is multiplied by the horizontal coordinate of each preset position and then added to obtain the final horizontal coordinate of the terminal to be located. The probability that the terminal to be located is located at each preset position is multiplied by the vertical coordinate of each preset position and then added to obtain the final vertical coordinate of the terminal to be located. According to the final horizontal coordinate and the final vertical coordinate of the terminal to be located, the final position of the terminal to be located is obtained.

[0078] On the basis of the above embodiments, the present embodiment trains the AdaBoost binary classifier according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons in the room received by the sample terminals at each preset position in the area, and obtains the trained AdaBoost binary classifier corresponding to each preset position, including: calculating the RSSI average value of the Bluetooth signals sent by each second Bluetooth beacon received by the sample terminal at any preset position at multiple times, and taking the second Bluetooth beacon corresponding to the maximum preset number of RSSI average values ​​as the target beacon;

[0079] like Figure 2 As shown, n preset positions are set indoors, and the training process of the AdaBoost binary classifier is described by taking position 1 as an example. When training the AdaBoost binary classifier corresponding to position 1, the RSSI of the Bluetooth signal sent by each second Bluetooth beacon received by the sample terminal at position 1 at multiple times is first obtained.

[0080] The parameters major and minor in the Bluetooth signal are used as a whole to uniquely identify the Bluetooth beacon. Figure 2 major+minor a : major+minor in [rssi1, rssi2, rssi3, rssi4,…] a represents the second Bluetooth beacon a, and the rssi sequence following the second Bluetooth beacon a represents the rssi of the Bluetooth signal sent by the second Bluetooth beacon a received by the sample terminal at position 1 at multiple times. The average value of the rssi sequence corresponding to each second Bluetooth beacon is calculated.

[0081] All second Bluetooth beacons corresponding to position 1 are sorted in descending order according to the average value of the RSSI sequence, and the first k second Bluetooth beacons are selected as target beacons. At the same time, the identifiers of the k second Bluetooth beacons are saved in the beacon sequence in descending order according to the average value of the RSSI sequence. The value of k is determined according to the actual situation.

[0082] The rssi of all the Bluetooth signals sent by the target beacons received by the sample terminal at the preset position at each moment is taken as a positive sample, and the rssi of all the Bluetooth signals sent by the target beacons received by the sample terminals at other preset positions in the room except the preset position at each moment is taken as a negative sample, and the AdaBoost binary classifier is trained to obtain the trained AdaBoost binary classifier corresponding to the preset position.

[0083] The RSSI at the same position of the RSSI sequence of the k second Bluetooth beacons in the beacon sequence is split into a feature sequence, thereby forming a k-dimensional feature sequence. The category corresponding to the feature sequence is 1, which is used as a positive sample. The same position corresponds to the same time

[0084] The RSSI sequence of the target beacon is selected from the RSSI sequences of the second Bluetooth beacons corresponding to other preset positions in the room except position 1, and arranged according to the order in the beacon sequence. Then, the RSSI at the same position in the RSSI sequence of the second Bluetooth beacon corresponding to each other preset position is split into a feature sequence, and the category corresponding to the feature sequence is 0, which is used as a negative sample.

[0085] Each feature sequence is used as the input of the AdaBoost binary classifier, and the AdaBoost binary classifier is sequenced. The number of AdaBoost binary classifiers is determined according to the actual situation. The above training process is performed for each preset position, thereby obtaining the following AdaBoost binary classifier set:

[0086]

[0087] On the basis of the above embodiment, in this embodiment, before taking the RSSI of the Bluetooth signals sent by all the target beacons received by the sample terminals at other preset positions other than the preset position at each moment in the room as negative samples, the method further includes: calculating a first ratio of the number of target beacons whose Bluetooth signals are not received by the sample terminals at the other preset positions to the total number of the target beacons;

[0088] In the process of filtering out the RSSI sequence of the target beacon from the RSSI sequences of the second Bluetooth beacons corresponding to other preset positions, if the Bluetooth signal of a target beacon is not received by the sample terminals at other preset positions, the RSSI sequence of the target beacon cannot be filtered out.

[0089] A first ratio of the number of target beacons in the beacon sequence that exist in the second Bluetooth beacons corresponding to other preset positions to the total number of target beacons is calculated, such as 50%.

[0090] When the first ratio is less than or equal to the first preset threshold and greater than 0, the RSSI corresponding to the target beacon whose Bluetooth signal is not received by the sample terminal at the other preset position is set to the first preset value;

[0091] If the first ratio is smaller, the values ​​in the RSSI sequence of the target beacon that does not exist in the second Bluetooth beacon corresponding to the other preset position are all set to preset values, such as -100.

[0092] When the first ratio is greater than the first preset threshold, the RSSI corresponding to the other preset positions is not taken as a negative sample.

[0093] If the first ratio is larger, the other preset positions are directly skipped, and negative samples are not determined based on the other positions, thereby greatly reducing the magnitude of the feature sequence data set and reducing the interference of irrelevant data.

[0094] On the basis of the above-mentioned embodiment, the method of calculating the average rssi of the Bluetooth signal sent by each second Bluetooth beacon received by the sample terminal at any preset position at multiple times in this embodiment includes: merging the rssi of the Bluetooth signal sent by each second Bluetooth beacon received by the sample terminal at each preset position at multiple times into the same sequence; aligning the rssi in each sequence according to the timestamp of the Bluetooth signal to which the rssi belongs;

[0095] Specifically, in the offline training stage, Bluetooth signals are collected at different preset positions indoors to obtain a training data set in the following format: Each preset position corresponds to Bluetooth signals sent by multiple Bluetooth beacons.

[0096]

[0097] Extract the four key fields of major, minor, rssi and time from the training data set. Among them, major and minor are used as a whole to uniquely identify a Bluetooth beacon, rssi represents the strength of the Bluetooth signal, and time represents the timestamp of the data. Then, merge the rssi data of the same second Bluetooth beacon at the same location into the same sequence. Align the rssi of different second Bluetooth beacons according to the timestamp time.

[0098] If the rssi corresponding to any timestamp in the aligned sequence is empty, fill the rssi corresponding to the timestamp with a second preset value;

[0099] When no Bluetooth signal of a second Bluetooth beacon is received at a certain moment, the RSSI of the Bluetooth signal of the second Bluetooth beacon is filled with a second preset value, such as -100.

[0100] In the case where a second ratio of the RSSIs in the padded sequence that are less than the second preset threshold to the total RSSIs in the sequence is greater than a third preset threshold, the sequence is deleted; and an average RSSI value in each retained sequence is calculated.

[0101] In the case where the second ratio of the RSSI sequence of a second Bluetooth beacon corresponding to a preset position is less than the second preset threshold, such as -80, is greater than the third preset threshold, such as 60%, it is considered that the second Bluetooth beacon is far away from the preset position. In order to reduce the interference of the Bluetooth beacon to the positioning result, the RSSI sequence of the second Bluetooth beacon is deleted from the RSSI sequence corresponding to the preset position.

[0102] Optionally, in order to reduce the impact of environmental noise, each RSSI sequence is filtered using Kalman filtering to obtain a valid training data set, as shown below:

[0103]

[0104] On the basis of the above embodiments, the method described in this embodiment obtains the distance between the terminal to be located and each first Bluetooth beacon based on the RSSI of the Bluetooth signal sent by multiple indoor first Bluetooth beacons received by the terminal to be located based on the signal attenuation model, including: fitting the parameters in the signal attenuation model according to the RSSI of the Bluetooth signal sent by each second Bluetooth coordinate received by the sample terminal at each preset position to obtain the parameters in the signal attenuation model; constructing the signal attenuation model corresponding to each second Bluetooth beacon according to the parameters in the signal attenuation model;

[0105] Specifically, in the offline training stage, the coordinates of each sampling position are preset positions in the room, which are known, and the position of each second Bluetooth beacon is also known. Therefore, the propagation distance d corresponding to each RSSI sequence can be obtained.

[0106] The RSSI sequences corresponding to the same second Bluetooth beacon at different sampling positions in the valid training data set are integrated together to obtain Figure 3 The data set on the left. The propagation distance d and its corresponding rssi sequence constitute a key-value pair.

[0107] Split the key-value pairs corresponding to each second Bluetooth beacon, and bring all or part of the split results into the signal attenuation model formula RSSI(d)=A+10ηlg(d). Use the least squares method to fit the parameters A and η. For the specific calculation method, see Figure 3 The formula in is used to obtain the signal attenuation model corresponding to each second Bluetooth beacon, forming the following signal attenuation model set:

[0108]

[0109] In the case that the first Bluetooth beacon exists in the second Bluetooth beacon, the distance between the terminal to be located and the first Bluetooth beacon is obtained according to the RSSI of the Bluetooth signal sent by the first Bluetooth beacon based on the signal attenuation model corresponding to the first Bluetooth beacon.

[0110] When calculating the distance between the terminal to be located and each first Bluetooth beacon, the first Bluetooth beacon is searched from the second Bluetooth beacons. If it exists, the RSSI of the Bluetooth signal sent by the first Bluetooth beacon is input into the signal attenuation model corresponding to the first Bluetooth beacon, and the distance d between the terminal to be located and the first Bluetooth beacon is output.

[0111] On the basis of the above embodiment, the method of acquiring the distance between the terminal to be located and each first Bluetooth beacon based on the RSSI of the Bluetooth signals sent by multiple first indoor Bluetooth beacons received by the terminal to be located based on the signal attenuation model in this embodiment includes: selecting the largest three RSSIs from the RSSIs of the Bluetooth signals sent by the multiple first Bluetooth beacons;

[0112] Specifically, three first Bluetooth beacons with the largest RSSI are selected from the valid test data set, and then the signal attenuation model corresponding to each selected first Bluetooth beacon is found from the signal attenuation model set to calculate the distance between the terminal to be located and each first Bluetooth beacon.

[0113] Input each of the three largest RSSIs into the signal attenuation model corresponding to the first Bluetooth beacon to which each RSSI belongs, and output the distance between the first Bluetooth beacon to which each RSSI belongs and the terminal to be located;

[0114] Each of the three RSSIs is input into a corresponding signal attenuation model, and the distance between the first Bluetooth beacon to which each RSSI belongs and the terminal to be located is output.

[0115] Correspondingly, the geometric method based on obtaining the initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon includes: obtaining the initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon based on the three-side positioning method.

[0116] The initial position (x, y) of the terminal to be located is calculated based on the three-side positioning method by using the distance between the terminal to be located and the three first Bluetooth beacons and the positions of the three first Bluetooth beacons.

[0117] This embodiment includes two stages: offline training and online positioning. The complete flow chart is as follows: Figure 4shown.

[0118] The Bluetooth indoor positioning device provided by the present invention is described below. The Bluetooth indoor positioning device described below and the Bluetooth indoor positioning method described above can be referred to each other.

[0119] like Figure 5 As shown, the device includes an acquisition module 501, a determination module 502 and a positioning module 503, wherein:

[0120] The acquisition module 501 is used to acquire the distance between the terminal to be located and each first Bluetooth beacon based on the RSSI of the Bluetooth signals sent by multiple first indoor Bluetooth beacons received by the terminal to be located based on the signal attenuation model;

[0121] The formula of the signal attenuation model is RSSI(d)=A+10ηlg(d). A and η are unknown parameters and can be obtained by data fitting. The RSSI of the Bluetooth signal sent by each first Bluetooth beacon received by the terminal to be located is used as the input of the signal attenuation model, that is, RSSI(d), and the distance d between the terminal to be located and each first Bluetooth beacon is obtained.

[0122] The determination module 502 is used to obtain the initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon based on a geometric method, and determine the area where the terminal to be located is located according to the initial position;

[0123] Since the position of each first Bluetooth beacon is known and the distance between the terminal to be located and each first Bluetooth beacon is known, the position (x, y) of the terminal to be located can be determined based on a geometric method and the determined position is used as the initial position.

[0124] The positioning module 503 is used to determine the final position of the terminal to be located based on the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons indoors and received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located.

[0125] Optionally, the fingerprint at each preset position is extracted according to the RSSI of the Bluetooth signal sent by the multiple second Bluetooth beacons in the room received by the sample terminal at each preset position in the area. The fingerprint of the terminal to be located is determined according to the RSSI of the Bluetooth signal sent by the multiple first Bluetooth beacons received by the terminal to be located. The fingerprint of the terminal to be located is compared with the fingerprints at each preset position to determine the final position of the terminal to be located.

[0126] In this embodiment, after first using a measurement-based Bluetooth indoor positioning method to determine the area where the terminal to be located is located, the indoor positioning method based on location fingerprint calculates the position of the terminal to be located according to the RSSI collected at a preset position in the area and the RSSI of the Bluetooth signal received by the terminal to be located. By combining the two positioning methods, the advantages of the two methods are complemented, thereby improving the accuracy and stability of the indoor positioning results.

[0127] On the basis of the above embodiments, the positioning module in this embodiment is used to: train the AdaBoost binary classifier according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons in the room and received by the sample terminals at each preset position in the area, and obtain the trained AdaBoost binary classifier corresponding to each preset position; input the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located into the trained AdaBoost binary classifier corresponding to each preset position in the area, and output the probability that the terminal to be located is located at each preset position; obtain the final position of the terminal to be located by multiplying the probability that the terminal to be located at each preset position by the coordinates of each preset position and adding them up.

[0128] On the basis of the above embodiments, the positioning module in this embodiment is used to: calculate the RSSI average value of the Bluetooth signal sent by each second Bluetooth beacon received by the sample terminal at any preset position at multiple times, and use the second Bluetooth beacon corresponding to the RSSI average value of the largest preset number as the target beacon; use the RSSI of the Bluetooth signals sent by all the target beacons received by the sample terminal at the preset position at each moment as the positive sample, and use the RSSI of the Bluetooth signals sent by all the target beacons received by the sample terminals at other preset positions in the room except the preset position at each moment as the negative sample, train the AdaBoost binary classifier, and obtain the trained AdaBoost binary classifier corresponding to the preset position.

[0129] Based on the above embodiment, this embodiment also includes a preprocessing module, which is used to calculate a first ratio of the number of target beacons whose Bluetooth signals are not received by the sample terminals at the other preset positions to the total number of target beacons; when the first ratio is less than or equal to the first preset threshold and greater than 0, the RSSI corresponding to the target beacon whose Bluetooth signal is not received by the sample terminals at the other preset positions is set to the first preset value; when the first ratio is greater than the first preset threshold, the RSSI corresponding to the other preset positions is not used as a negative sample.

[0130] On the basis of the above embodiments, the positioning module in this embodiment is used to: merge the RSSIs of Bluetooth signals sent by each second Bluetooth beacon received by the sample terminal at each preset position at multiple times into the same sequence; align the RSSIs in each sequence according to the timestamp of the Bluetooth signal to which the RSSIs belong; if the RSSI corresponding to any timestamp in the aligned sequence is empty, fill the RSSI corresponding to the timestamp with a second preset value; if the second ratio of the RSSIs in the filled sequence that are less than the second preset threshold to the total RSSIs in the sequence is greater than a third preset threshold, delete the sequence; and calculate the RSSI average value in each retained sequence.

[0131] On the basis of the above embodiments, the acquisition module in this embodiment is used to: fit the parameters in the signal attenuation model according to the RSSI of the Bluetooth signal sent by each second Bluetooth coordinate received by the sample terminal at each preset position in the room, and obtain the parameters in the signal attenuation model; construct a signal attenuation model corresponding to each second Bluetooth beacon according to the parameters in the signal attenuation model; when there is a first Bluetooth beacon in the second Bluetooth beacon, obtain the distance between the terminal to be located and the first Bluetooth beacon based on the signal attenuation model corresponding to the first Bluetooth beacon and the RSSI of the Bluetooth signal sent by the first Bluetooth beacon.

[0132] Based on the above embodiments, the acquisition module in this embodiment is used to: select the three largest RSSIs from the RSSIs of the Bluetooth signals sent by the multiple first Bluetooth beacons; input each of the three largest RSSIs into the signal attenuation model corresponding to the first Bluetooth beacon to which each RSSI belongs, and output the distance between the first Bluetooth beacon to which each RSSI belongs and the terminal to be located; accordingly, the determination module is used to: obtain the initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon based on the three-side positioning method.

[0133] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the Bluetooth indoor positioning method, which includes: obtaining the distance between the terminal to be positioned and each first Bluetooth beacon based on the signal attenuation model according to the RSSI of the Bluetooth signal sent by multiple indoor first Bluetooth beacons received by the terminal to be positioned; obtaining the initial position of the terminal to be positioned according to the distance between the terminal to be positioned and each first Bluetooth beacon based on the geometric method, and determining the area where the terminal to be positioned is located according to the initial position; determining the final position of the terminal to be positioned according to the RSSI of the Bluetooth signal sent by the multiple indoor second Bluetooth beacons received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signal sent by the multiple first Bluetooth beacons received by the terminal to be positioned.

[0134] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, 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, and the computer software product is stored in a storage medium, including a number of 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 invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0135] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the Bluetooth indoor positioning method provided by the above-mentioned methods, and the method includes: based on a signal attenuation model, according to the RSSI of the Bluetooth signals sent by multiple first indoor Bluetooth beacons received by the terminal to be located, the distance between the terminal to be located and each first Bluetooth beacon is obtained; based on a geometric method, the initial position of the terminal to be located is obtained according to the distance between the terminal to be located and each first Bluetooth beacon, and the area where the terminal to be located is determined according to the initial position; according to the RSSI of the Bluetooth signals sent by the multiple second indoor Bluetooth beacons received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located, the final position of the terminal to be located is determined.

[0136] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the above-mentioned Bluetooth indoor positioning methods, the method comprising: obtaining the distance between the terminal to be located and each first Bluetooth beacon based on the RSSI of the Bluetooth signals sent by multiple first indoor Bluetooth beacons received by the terminal to be located based on a signal attenuation model; obtaining the initial position of the terminal to be located based on the distance between the terminal to be located and each first Bluetooth beacon based on a geometric method, and determining the area where the terminal to be located is located based on the initial position; determining the final position of the terminal to be located based on the RSSI of the Bluetooth signals sent by the multiple second indoor Bluetooth beacons received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located.

[0137] The device embodiments described above are merely illustrative, 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. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A Bluetooth indoor positioning method, characterized in that: include: Based on the signal attenuation model, according to the RSSI of the Bluetooth signals sent by the multiple first indoor Bluetooth beacons received by the terminal to be located, the distance between the terminal to be located and each first Bluetooth beacon is obtained; Acquire the initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon based on a geometric method, and determine the area where the terminal to be located is located according to the initial position; Determine the final position of the terminal to be located according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons indoors and received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons and received by the terminal to be located; The method of determining the final position of the terminal to be located according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons indoors and received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons and received by the terminal to be located comprises: Training the AdaBoost binary classifier according to the RSSI of the Bluetooth signals sent by the plurality of second Bluetooth beacons indoors and received by the sample terminals at the preset positions in the area, and obtaining the trained AdaBoost binary classifier corresponding to each preset position; Inputting the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located into the trained AdaBoost binary classifier corresponding to each preset position in the area, and outputting the probability that the terminal to be located is located at each preset position; Obtaining a final position of the terminal to be located by multiplying the probability that the terminal to be located is located at each preset position by the coordinates of each preset position and then adding them; The AdaBoost binary classifier is trained according to the RSSI of the Bluetooth signals sent by the plurality of second indoor Bluetooth beacons received by the sample terminals at the preset positions in the area, and the trained AdaBoost binary classifier corresponding to each preset position is obtained, including: Calculate the RSSI average value of the Bluetooth signal sent by each second Bluetooth beacon received by the sample terminal at any preset position at multiple times, and use the second Bluetooth beacon corresponding to the largest preset number of RSSI average values ​​as the target beacon; The rssi of all the Bluetooth signals sent by the target beacons received by the sample terminal at the preset position at each moment is taken as a positive sample, and the rssi of all the Bluetooth signals sent by the target beacons received by the sample terminals at other preset positions in the room except the preset position at each moment is taken as a negative sample, and the AdaBoost binary classifier is trained to obtain the trained AdaBoost binary classifier corresponding to the preset position.

2. The Bluetooth indoor positioning method according to claim 1, characterized in that: Before taking the RSSI of the Bluetooth signals sent by all the target beacons received by the sample terminals at other preset positions in the room except the preset position at each moment as negative samples, the method further includes: Calculate a first ratio of the number of target beacons whose Bluetooth signals are not received by the sample terminals at the other preset positions to the total number of the target beacons; When the first ratio is less than or equal to the first preset threshold and greater than 0, the RSSI corresponding to the target beacon whose Bluetooth signal is not received by the sample terminal at the other preset position is set to the first preset value; When the first ratio is greater than the first preset threshold, the RSSI corresponding to the other preset positions is not taken as a negative sample.

3. The Bluetooth indoor positioning method according to claim 1, characterized in that: The calculating the RSSI average value of the Bluetooth signal sent by each second Bluetooth beacon received by the sample terminal at any preset position at multiple times includes: Combining the RSSIs of the Bluetooth signals sent by the second Bluetooth beacons received by the sample terminal at each preset position at multiple times into the same sequence; Align the rssi in each sequence according to the timestamp of the bluetooth signal to which the rssi belongs; If the rssi corresponding to any timestamp in the aligned sequence is empty, fill the rssi corresponding to the timestamp with a second preset value; In a case where a second ratio of the RSSIs in the padded sequence that are less than the second preset threshold to the total number of RSSIs in the sequence is greater than a third preset threshold, deleting the sequence; Calculate the average rssi value in each retained sequence.

4. The Bluetooth indoor positioning method according to any one of claims 1 to 3, characterized in that: The method of obtaining the distance between the terminal to be located and each first Bluetooth beacon based on the RSSI of the Bluetooth signals sent by the plurality of first indoor Bluetooth beacons received by the terminal to be located based on the signal attenuation model includes: According to the RSSI of the Bluetooth signal sent by each second Bluetooth coordinate received by the sample terminal at each preset position in the room, the parameters in the signal attenuation model are fitted to obtain the parameters in the signal attenuation model; Constructing a signal attenuation model corresponding to each second Bluetooth beacon according to the parameters in the signal attenuation model; In the case that the first Bluetooth beacon exists in the second Bluetooth beacon, the distance between the terminal to be located and the first Bluetooth beacon is obtained according to the RSSI of the Bluetooth signal sent by the first Bluetooth beacon based on the signal attenuation model corresponding to the first Bluetooth beacon.

5. The Bluetooth indoor positioning method according to claim 4, characterized in that: The method of obtaining the distance between the terminal to be located and each first Bluetooth beacon based on the RSSI of the Bluetooth signals sent by the plurality of first indoor Bluetooth beacons received by the terminal to be located based on the signal attenuation model includes: Selecting the three largest RSSIs from the RSSIs of the Bluetooth signals sent by the plurality of first Bluetooth beacons; Input each of the three largest RSSIs into the signal attenuation model corresponding to the first Bluetooth beacon to which each RSSI belongs, and output the distance between the first Bluetooth beacon to which each RSSI belongs and the terminal to be located; Accordingly, the obtaining the initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon based on the geometric method includes: The initial position of the terminal to be located is acquired according to the distance between the terminal to be located and each first Bluetooth beacon based on the three-side positioning method.

6. A Bluetooth indoor positioning device, characterized in that: include: An acquisition module, configured to acquire the distance between the terminal to be located and each first Bluetooth beacon based on the RSSI of the Bluetooth signals sent by the multiple first indoor Bluetooth beacons received by the terminal to be located based on a signal attenuation model; A determination module, configured to obtain an initial position of the terminal to be located according to the distance between the terminal to be located and each first Bluetooth beacon based on a geometric method, and determine an area where the terminal to be located is located according to the initial position; A positioning module, used to determine the final position of the terminal to be located according to the RSSI of the Bluetooth signals sent by the multiple second Bluetooth beacons in the room received by the sample terminals at each preset position in the area and the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located; The positioning module is specifically used for: Training the AdaBoost binary classifier according to the RSSI of the Bluetooth signals sent by the plurality of second Bluetooth beacons indoors and received by the sample terminals at the preset positions in the area, and obtaining the trained AdaBoost binary classifier corresponding to each preset position; Inputting the RSSI of the Bluetooth signals sent by the multiple first Bluetooth beacons received by the terminal to be located into the trained AdaBoost binary classifier corresponding to each preset position in the area, and outputting the probability that the terminal to be located is located at each preset position; Obtaining a final position of the terminal to be located by multiplying the probability that the terminal to be located is located at each preset position by the coordinates of each preset position and then adding them; The AdaBoost binary classifier is trained according to the RSSI of the Bluetooth signals sent by the plurality of second indoor Bluetooth beacons received by the sample terminals at the preset positions in the area, and the trained AdaBoost binary classifier corresponding to each preset position is obtained, including: Calculate the RSSI average value of the Bluetooth signal sent by each second Bluetooth beacon received by the sample terminal at any preset position at multiple times, and use the second Bluetooth beacon corresponding to the largest preset number of RSSI average values ​​as the target beacon; The rssi of all the Bluetooth signals sent by the target beacons received by the sample terminal at the preset position at each moment is taken as a positive sample, and the rssi of all the Bluetooth signals sent by the target beacons received by the sample terminals at other preset positions in the room except the preset position at each moment is taken as a negative sample, and the AdaBoost binary classifier is trained to obtain the trained AdaBoost binary classifier corresponding to the preset position.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the Bluetooth indoor positioning method according to any one of claims 1 to 5 are implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the Bluetooth indoor positioning method according to any one of claims 1 to 5 are implemented.

Images