Bluetooth-based positioning method and device, and storage medium

Abstract

The invention discloses a Bluetooth-based positioning method and device, and a storage medium. The method comprises the following steps: receiving an original Bluetooth beacon signal, a wireless fidelity signal and an acceleration signal; generating a first signal sequence representing the change trend of the first received signal strength indication value according to the original Bluetooth beacon signal; generating a second signal sequence representing a change trend of a second received signal strength indication value according to the wireless fidelity signal; generating a third signal sequence representing the jitter state according to the acceleration signal; selecting a filtering set according to the first signal sequence, the second signal sequence and the third signal sequence; calling a filtering algorithm to filter the original Bluetooth beacon signal to obtain a candidate Bluetooth beacon signal; screening out a plurality of candidate Bluetooth beacon signals with the highest quality value according to the first received signal strength indication value, and taking the candidate Bluetooth beacon signals as target Bluetooth beacon signals; and positioning according to the target Bluetooth beacon signal. According to the embodiment, the filtering effect is improved, and the performance of the Bluetooth beacon signal is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of Bluetooth, and in particular to a positioning method, device and storage medium based on Bluetooth. Background Art

[0002] Mobile terminals such as mobile phones and watches are widely used in people's lives and work. In places such as shopping malls and underground streets, Bluetooth is usually used to provide LBS (Location Based Services) services for mobile terminals, such as child protection, navigation, electronic fences, games, etc.

[0003] Bluetooth-based positioning technology usually filters the Bluetooth beacon signal broadcast by the base station, solves the RSSI (Received Signal Strength Indication) of the filtered Bluetooth beacon signal, and obtains the coordinates of the mobile terminal.

[0004] At present, filtering processing is usually improved and integrated based on the native filtering algorithm for a specific environment. However, the environment of mobile terminals is constantly changing, and the environment in places such as shopping malls and underground streets is relatively complex. There are building obstructions and a large amount of Wi-Fi (Wireless Fidelity) signal interference. The running of children and other users will increase the disturbance. The use of fixed filtering algorithms has limitations, and the degree of match with the environmental state and the own state is low, resulting in low Bluetooth-based positioning accuracy. Summary of the invention

[0005] In view of this, the present invention provides a Bluetooth-based positioning method, device and storage medium to improve the accuracy of Bluetooth-based positioning.

[0006] A first aspect of the present invention provides a Bluetooth-based positioning method, comprising:

[0007] Respectively receive external original Bluetooth beacon signals, wireless fidelity signals, and internal acceleration signals;

[0008] Generating a first signal sequence representing a change trend of a first received signal strength indicator value according to the original Bluetooth beacon signal;

[0009] generating a second signal sequence representing a change trend of a second received signal strength indicator value according to the wireless fidelity signal;

[0010] generating a third signal sequence representing a shaking state according to the acceleration signal;

[0011] Selecting a filter set according to the first signal sequence, the second signal sequence and the third signal sequence; the filter set contains one or more filter algorithms;

[0012] Calling one or more of the filtering algorithms in sequence to filter the original Bluetooth beacon signal to obtain a candidate Bluetooth beacon signal;

[0013] Filtering, according to the first received signal strength indicator value, a plurality of the candidate Bluetooth beacon signals with the highest positioning quality values ​​as target Bluetooth beacon signals;

[0014] Positioning is performed according to the target Bluetooth beacon signal to obtain target coordinate information.

[0015] A second aspect of the present invention provides a Bluetooth-based positioning device, comprising:

[0016] A signal receiving module, used to receive external original Bluetooth beacon signals, wireless fidelity signals, and internal acceleration signals respectively;

[0017] A first signal sequence generating module, configured to generate a first signal sequence representing a change trend of a first received signal strength indicator value according to the original Bluetooth beacon signal;

[0018] A second signal sequence generating module, configured to generate a second signal sequence representing a change trend of a second received signal strength indicator value according to the wireless fidelity signal;

[0019] A third signal sequence generating module, configured to generate a third signal sequence representing a shaking state according to the acceleration signal;

[0020] A filter set selection module, configured to select a filter set according to the first signal sequence, the second signal sequence and the third signal sequence; the filter set includes one or more filter algorithms;

[0021] A filtering processing module, used to sequentially call one or more of the filtering algorithms to filter the original Bluetooth beacon signal to obtain a candidate Bluetooth beacon signal;

[0022] A beacon signal screening module, configured to screen out a plurality of candidate Bluetooth beacon signals having the highest positioning quality values ​​according to the first received signal strength indicator value as target Bluetooth beacon signals;

[0023] The Bluetooth positioning module is used to perform positioning according to the target Bluetooth beacon signal to obtain target coordinate information.

[0024] A third aspect of the present invention provides an electronic device, the electronic device comprising:

[0025] at least one processor; and

[0026] a memory communicatively connected to the at least one processor; wherein,

[0027] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the Bluetooth-based positioning method as described in the first aspect above.

[0028] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the Bluetooth-based positioning method as described in the first aspect above is implemented.

[0029] A fifth aspect of the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the Bluetooth-based positioning method as described in the first aspect above.

[0030] In this embodiment, an external original Bluetooth beacon signal, a wireless fidelity signal, and an internal acceleration signal are respectively received; a first signal sequence representing a changing trend of a first received signal strength indicator value is generated according to the original Bluetooth beacon signal; a second signal sequence representing a changing trend of a second received signal strength indicator value is generated according to the wireless fidelity signal; a third signal sequence representing a jitter state is generated according to the acceleration signal; a filter set is selected according to the first signal sequence, the second signal sequence, and the third signal sequence; the filter set contains one or more filtering algorithms; one or more filtering algorithms are called in turn to filter the original Bluetooth beacon signal to obtain a candidate Bluetooth beacon signal; a plurality of candidate Bluetooth beacon signals with the highest positioning quality values ​​are screened out according to the first received signal strength indicator value as target Bluetooth beacon signals; positioning is performed according to the target Bluetooth beacon signal to obtain target coordinate information. This embodiment comprehensively evaluates the environmental state and the own state from the RSSI of the Bluetooth beacon signal, the RSSI of the Wi-Fi signal and the acceleration signal, and selects a suitable filtering algorithm to filter the Bluetooth beacon signal. It has high flexibility, effectively improves the matching degree with the environmental state and the own state, improves the filtering effect, improves the performance of the Bluetooth beacon signal, and evaluates the quality of positioning based on the RSSI of the Bluetooth beacon signal, and can screen out Bluetooth beacon signals with higher quality for positioning, which can effectively improve the accuracy of Bluetooth-based positioning.

[0031] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 This is a flowchart of a Bluetooth-based positioning method provided in Example 1 of the present invention.

[0034] Figure 2 It is a structural diagram of a filtering classification network provided in Example 1 of the present invention.

[0035] Figure 3 It is a structural diagram of a Bluetooth-based positioning device provided in Embodiment 2 of the present invention.

[0036] Figure 4 It is a structural schematic diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can cover sequential implementations other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] Embodiment 1

[0040] See also Figure 1, shows a flowchart of a Bluetooth-based positioning method provided by Embodiment 1 of the present invention. The method can be executed by a Bluetooth-based positioning device. The Bluetooth-based positioning device can be implemented in the form of hardware and / or software. The Bluetooth-based positioning device can be configured in an electronic device, which can be a server or a mobile terminal. Figure 1 As shown, the method includes:

[0041] Step 101: Receive an external original Bluetooth beacon signal, a wireless fidelity signal, and an internal acceleration signal respectively.

[0042] like Figure 2 As shown, components such as a Bluetooth module, a Wi-Fi module, and an acceleration sensor are set in a mobile terminal. When the mobile terminal starts the LBS, the Bluetooth module can be called to receive the original Bluetooth beacon signal broadcast by an external base station, the Wi-Fi module can be called to receive the wireless fidelity signal broadcast by an external AP (Wireless Access Point), and the acceleration signal generated by the internal acceleration sensor can be read.

[0043] For mobile terminals with low computing resources such as watches, this embodiment can be applied to the server to receive the original Bluetooth beacon signals, wireless fidelity signals and acceleration signals uploaded by mobile terminals such as watches, perform calculations in the server, provide positioning services for mobile terminals such as watches, and send target coordinate information to mobile terminals such as watches.

[0044] For user-end devices with high computing resources such as mobile phones, this embodiment can be applied to mobile terminals such as mobile phones, perform calculations in mobile terminals such as mobile phones, and provide positioning services for mobile terminals such as mobile phones.

[0045] Step 102: Generate a first signal sequence representing a change trend of a first received signal strength indicator value according to the original Bluetooth beacon signal.

[0046] If there are factors such as building obstruction, Wi-Fi signal interference, and the user's mobile terminal movement, the impact of these factors will be comprehensively reflected in the first received signal strength indicator (RSSI) of the original Bluetooth beacon signal. Figure 2 As shown, the first received signal strength indicator (RSSI) of the original Bluetooth beacon signal can be statistically analyzed to generate a first signal sequence Sequence_1 representing the change trend of the first received signal strength indicator (RSSI).

[0047] In a specific implementation, a window may be added to the first RSSI of each original Bluetooth beacon signal, and the average value of the first RSSI in the window of the same original Bluetooth beacon signal may be calculated to obtain the Bluetooth RSSI.

[0048] Generally, a Bluetooth beacon signal with a higher RSSI is selected for positioning processing. Therefore, multiple Bluetooth beacon signals with the highest Bluetooth received signal strength indicator values ​​can be screened out for statistical analysis.

[0049] On the one hand, for multiple Bluetooth beacon signals with the highest Bluetooth received signal strength indicator values, an average value of the first received signal strength indicator values ​​at the same time can be calculated to obtain the first co-located received signal strength indicator value.

[0050] On the other hand, for multiple Bluetooth beacon signals with the highest Bluetooth received signal strength indication values, the minimum and maximum values ​​of the first received signal strength indication values ​​at the same time are statistically analyzed respectively, so as to form a first co-location fluctuation amplitude with the minimum and maximum values ​​of the first received signal strength indication values ​​at the same time.

[0051] The first co-located received signal strength indicator values ​​at each moment are concatenated with the first co-located fluctuation amplitudes at each moment, thereby forming a first signal sequence representing a variation trend of the first received signal strength indicator values.

[0052] Step 103: Generate a second signal sequence representing a change trend of a second received signal strength indicator value according to the wireless fidelity signal.

[0053] In places such as shopping malls and underground streets, merchants will use a large number of routers, mobile phones, etc. as APs to access other smart devices, which will generate a large number of Wi-Fi signals. Wi-Fi and Bluetooth may both use the 2.4GHz frequency band at the same time. The Wi-Fi channel overlaps with the Bluetooth frequency, making the Wi-Fi signal one of the main causes of interference to Bluetooth-based positioning processing. In particular, when the Wi-Fi signal is strong and continuously transmitted, it may mask the Bluetooth signal and cause Bluetooth data packet loss.

[0054] So, if Figure 2 As shown, the second received signal strength indicator (RSSI) of the Wi-Fi signal may be statistically analyzed to generate a second signal sequence Sequence_2 representing a change trend of the second received signal strength indicator (RSSI).

[0055] In a specific implementation, since the Wi-Fi signals broadcast by each AP may interfere with the Bluetooth signal, the number of wireless fidelity signals broadcast by the AP may be counted at each moment.

[0056] For each wireless fidelity signal, an average value of second received signal strength indication values ​​(RSSI) at the same time is calculated to obtain a second co-located received signal strength indication value.

[0057] For each Wi-Fi signal, the minimum value and the maximum value of the second received signal strength indicator value at the same time are respectively counted, so as to form a second co-location fluctuation amplitude with the minimum value and the maximum value of the second received signal strength indicator value at the same time.

[0058] The second co-located received signal strength indicator values ​​of various numbers and at various times and the second co-located fluctuation amplitudes at various times are combined into a second signal sequence representing the variation trend of the second received signal strength indicator values.

[0059] Step 104: Generate a third signal sequence representing the shaking state according to the acceleration signal.

[0060] When a user moves around with a mobile terminal such as a watch, if the mobile terminal shakes significantly, the distance and angle between the mobile terminal and the base station may change significantly in a short period of time, causing the RSSI of the Bluetooth beacon signal to fluctuate, making the jitter one of the main causes of interference to the Bluetooth-based positioning processing.

[0061] So, if Figure 2 As shown, the acceleration signal can be statistically analyzed to generate a third signal sequence Sequence_3 representing the shaking state.

[0062] In a specific implementation, the acceleration sensor can collect acceleration signals in the X direction, the Y direction, and the Z direction at the same time. When moving, the jitter of mobile terminals such as watches mainly occurs in the Z direction. Therefore, the acceleration signal in the Z direction is amplified, for example, the acceleration signal in the Z direction is multiplied by a preset amplification factor, where the amplification factor is greater than 1.

[0063] At the same time, the acceleration signal amplified in the Z direction is added to the sum of the acceleration signal in the X direction and the acceleration signal in the Y direction to obtain the jitter value.

[0064] The jitter values ​​at various moments are combined into a third signal sequence representing the jitter state.

[0065] Step 105 : Select a filter set according to the first signal sequence, the second signal sequence, and the third signal sequence.

[0066] In this embodiment, different filtering algorithms can be used in different environments to conduct Bluetooth positioning experiments on mobile terminals. A better filtering algorithm can be selected based on the performance indicators of the experiment (such as positioning accuracy) to build a filtering library, where the filtering library has multiple filtering sets, and each filtering set contains one or more filtering algorithms.

[0067] The filtering algorithms in the same filtering set are used for Bluetooth positioning at the same time. When the filtering set contains at least two filtering algorithms, the filtering set limits the order of the filtering algorithms by setting the order of the filtering algorithms to the order of the filtering algorithms.

[0068] Exemplarily, the filtering algorithms include the following types:

[0069] 1. Kalman Filter and Extended Kalman Filter (EKF)

[0070] Kalman filtering estimates the optimal state by combining the state equation and the observation equation with the predicted and measured values. A single Kalman filter is suitable for processing linear systems and Gaussian noise and is often used for dynamic positioning.

[0071] The extended Kalman filter is an extension of the Kalman filter. It handles nonlinear problems through linearization. A single extended Kalman filter is suitable for nonlinear systems, such as positioning in complex environments and positioning when users move their mobile terminals significantly.

[0072] 2. Gaussian Filter

[0073] Gaussian filtering selects weights for linear smoothing according to the shape of the Gaussian function. It is a filter based on the Gaussian normal distribution.

[0074] 3. Particle Filter

[0075] Particle filtering represents state distribution through a large number of particles and is suitable for nonlinear and non-Gaussian noise.

[0076] A single particle filter is suitable for positioning in complex environments.

[0077] 4. Low-pass Filter

[0078] Low-pass filtering is to filter out high-frequency noise and retain low-frequency signals. A single low-pass filter is suitable for removing high-frequency noise in Bluetooth beacon signals.

[0079] 5. Moving Average Filter

[0080] Moving average filtering takes the average value of the signal over a period of time to smooth the data. A single moving average filter is suitable for removing short-term fluctuations in Bluetooth beacon signals and retaining long-term trends.

[0081] When the noise of the Bluetooth beacon signal is large and the system changes dynamically, a filter set of Kalman filtering and low-pass filtering can be used for filtering.

[0082] When performing high-precision positioning in a complex environment, a filter set consisting of an extended Kalman filter and a particle filter can be used for filtering.

[0083] When the Bluetooth beacon signal fluctuates greatly and relies on smoothing, a filter set of moving average filtering and Kalman filtering can be used for filtering.

[0084] When the indoor environment is highly complex and the base stations are sparse, a filter set of particle filtering, Kalman filtering and low-pass filtering can be used for filtering.

[0085] Of course, the above filter sets are only used as examples. When implementing this embodiment, other filter sets can be set according to actual conditions, and this embodiment does not limit this. In addition, in addition to the above filter sets, those skilled in the art can also use other filter sets according to actual needs, and this embodiment does not limit this.

[0086] In this embodiment, the first signal sequence, the second signal sequence, and the third signal sequence may be combined to evaluate the state of the environment in which the mobile terminal is located, thereby selecting a filter set suitable for the current environment state in the filter library.

[0087] In a specific implementation, when conducting Bluetooth positioning experiments on mobile terminals using different filtering algorithms in different environments, the experimental data (i.e., the first signal sequence, the second signal sequence, and the third signal sequence, as well as the selected filter set) are used to train a multi-classification deep learning model as a filtering classification network.

[0088] like Figure 2 As shown, the type of the filtering classification network is a convolutional neural network (CNN), which includes a first convolutional layer Conv_1, a second convolutional layer Conv_2, a third convolutional layer Conv_3, a fourth convolutional layer Conv_4, a depthwise separable convolutional layer (Depthwise Conv, DConv) and a fully connected layer (Fully Connected Layer, FC).

[0089] Among them, the first convolutional layer Conv_1, the second convolutional layer Conv_2, the third convolutional layer Conv_3 and the fourth convolutional layer Conv_4 are all convolutional layers. Their main operation is to perform a sliding convolution operation on the input data through a convolution kernel (also called a filter). The convolution kernel is a two-dimensional matrix. During the sliding process, the convolution kernel is multiplied element by element with the corresponding area of ​​the input data and the sum is calculated to obtain an output value. This process is repeated continuously to finally generate a feature map after convolution, thereby extracting the local features of the input data.

[0090] The depthwise separable convolution layer DCnv decomposes the standard convolution operation into depthwise convolution and pointwise convolution. The depthwise convolution is to apply a convolution kernel to each channel of the input to perform a convolution operation, generating a feature map with the same number of input channels. The depthwise convolution is mainly used to extract the spatial features of the input data. The pointwise convolution is to use a 1×1 convolution kernel to perform a convolution operation on the output of the depthwise convolution, combining the features of different channels to generate the final feature map. The pointwise convolution is mainly used to adjust the number of channels.

[0091] The computational complexity and number of parameters of the depthwise separable convolutional layer DConv are significantly reduced, making the filtering classification network more lightweight and suitable for running on resource-constrained mobile terminals.

[0092] Furthermore, the first convolution layer Conv_1, the second convolution layer Conv_2, the third convolution layer Conv_3 and the depthwise separable convolution layer DConv can all be configured with activation functions such as ReLU (Rectified Linear Unit, linear rectification function) to achieve activation operations.

[0093] When selecting a filter set, you can determine the filter classification network and load the filter classification network to run.

[0094] The first signal sequence Sequence_1 is converted into the first feature map FeatureMap_1 by using Reshape (matrix transformation) and the first feature map FeatureMap_1 is input into the first convolution layer Conv_1 to perform convolution operation and activation operation in sequence to obtain the Bluetooth beacon features.

[0095] The second signal sequence Sequence_2 is converted into a second feature map FeatureMap_2 by using Reshape (matrix transformation) or other methods, and the second feature map FeatureMap_2 is input into the second convolutional layer Conv_2 to perform convolution operations and activation operations in sequence to obtain wireless fidelity features.

[0096] The third signal sequence Sequence_3 is converted into a third feature map FeatureMap_3 by using methods such as Reshape (matrix transformation), and the third feature map FeatureMap_3 is input into the third convolutional layer Conv_3 to perform convolution operations and activation operations in sequence to obtain jitter features.

[0097] The first signal sequence Sequence_1, the second signal sequence Sequence_2 and the third signal sequence Sequence_3 are all one-dimensional sequence data, which reflect the linear order relationship between the data. It is difficult to express the local patterns or structures that may exist in the data (such as the fluctuation of Bluetooth beacon signals, the fluctuation of Wi-Fi signals, etc.). Converting the one-dimensional sequence data into two-dimensional feature maps (i.e., the first feature map FeatureMap_1, the second feature map FeatureMap_2 and the third feature map FeatureMap_3) can reorganize the data, which not only retains the time sequence information, but also makes the originally hidden local structure more obvious. In addition, the two-dimensional feature map can be adapted to CNN to give full play to the ability of CNN in extracting local features of feature maps.

[0098] Use functions such as Concat to merge Bluetooth beacon features, wireless fidelity features, and jitter features into original multimodal features.

[0099] The original multimodal features are input into the depth-wise separable convolutional layer DConv, which performs convolution and activation operations in sequence to obtain candidate multimodal features.

[0100] The candidate multimodal features are input into the fourth convolutional layer Conv_4 to perform a convolution operation to obtain the target multimodal features.

[0101] The target multimodal features are input into the fully connected layer FC and mapped into classification features. The classification features are activated using activation functions such as Sigmoid (S-type function) to obtain the probabilities of each filter set, and the filter set with the highest probability is output as the selected filter set.

[0102] Step 106: Call one or more filtering algorithms in sequence to filter the original Bluetooth beacon signal to obtain a candidate Bluetooth beacon signal.

[0103] When a filter set is selected, one or more filter algorithms may be called in sequence according to the instructions of the filter set to filter the original Bluetooth beacon signal (especially RSSI) to obtain a candidate Bluetooth beacon signal.

[0104] Step 107: Filter out multiple candidate Bluetooth beacon signals with the highest positioning quality values ​​according to the first received signal strength indicator value as target Bluetooth beacon signals.

[0105] In practical applications, the positioning quality of each candidate Bluetooth beacon signal can be evaluated according to the changing trend of the first received signal strength indication value to obtain a quality value, thereby selecting multiple candidate Bluetooth beacon signals with the highest quality values ​​and recording them as target Bluetooth beacon signals, thereby improving the accuracy of Bluetooth positioning.

[0106] In one embodiment of the present invention, step 107 may include the following steps:

[0107] Step 1071: Determine a beacon detection network.

[0108] In this embodiment, a recurrent neural network (RNN) may be trained as a beacon detection network in an offline environment, so that the beacon detection network has the ability to detect the quality value of the Bluetooth beacon signal in positioning.

[0109] Among them, the structure of the beacon detection network is not limited to artificially designed recurrent neural networks, such as LSTM (Long Short-Term Memory), GRU (Gate Recurrent Unit), etc., and can also be a recurrent neural network optimized by a model quantization method, a recurrent neural network that searches for the characteristics of Bluetooth beacon signals by a NAS (Neural Architecture Search) method, etc. This embodiment does not impose any restrictions on this.

[0110] When detecting the quality value of the candidate Bluetooth beacon signal, the beacon detection network operation can be loaded.

[0111] In one embodiment of the present invention, step 1071 may further include the following steps:

[0112] Step 10711: Sample any two frames of sample Bluetooth beacon signals as a sample set.

[0113] In this embodiment, if there are multiple base stations broadcasting test Bluetooth beacon signals in the same scene, a suitable filter set can be used to filter the test Bluetooth beacon signal to obtain a sample Bluetooth beacon signal. At this time, the Bluetooth device can use any sample Bluetooth beacon signal for positioning, then any two frames of sample Bluetooth beacon signals can be sampled from multiple sample Bluetooth beacon signals as a sample set.

[0114] Step 10712: label the sample set with a quality label according to the positioning accuracy of the sample Bluetooth beacon signal.

[0115] In this embodiment, the positioning accuracy of the sample Bluetooth beacon signal can be evaluated in the scenario, and the sample set can be sorted according to the positioning accuracy of the sample Bluetooth beacon signal to mark the quality label, wherein the quality label indicates that the positioning accuracy of one frame of the sample Bluetooth beacon signal is better than the positioning accuracy of another frame of the sample Bluetooth beacon signal.

[0116] In a specific implementation, in the same scenario, two frames of sample Bluetooth beacon signals in the sample set are respectively combined with n-1 frames of reference Bluetooth beacon signals to form two test beacon sets; wherein the scenario is configured with actual coordinate information of the Bluetooth device.

[0117] The Bluetooth device is positioned according to each test beacon set to obtain the test coordinate information.

[0118] The difference between each actual coordinate information and the test coordinate information is calculated to obtain the single point positioning offset.

[0119] Repeat the test multiple times in the same manner as above to accumulate multiple single-point positioning offsets.

[0120] For each frame sample Bluetooth beacon signal, the average value of the single-point positioning offset is calculated to obtain the overall positioning offset.

[0121] The overall positioning offsets of the two frames of sample Bluetooth beacon signals in the sample set are compared, and the sample set is annotated with a quality label that the positioning accuracy of the sample Bluetooth beacon signal with a smaller overall positioning offset is better than the positioning accuracy of the sample Bluetooth beacon signal with a larger overall positioning offset.

[0122] Step 10713: input the third received signal strength indicator values ​​of the two frames of sample Bluetooth beacon signals in the sample set into the beacon detection network to detect the quality values ​​of the sample Bluetooth beacon signals in positioning.

[0123] The third received signal strength indicator values ​​(sequences) of the two frames of sample Bluetooth beacon signals in the sample set are respectively input into the beacon detection network, and the beacon detection network respectively detects the positioning quality values ​​of the two frames of sample Bluetooth beacon signals.

[0124] Step 10714: Generate a pairing loss value based on the quality value and the quality label.

[0125] For the same sample set, the quality value and quality label can be substituted into the preset pairwise ranking loss function (Pairwise Ranking Loss Function) for calculation to obtain the pairwise loss value.

[0126] Among them, the pairing loss functions include Hinge Loss, Contrastive Loss, RankNet Loss, and so on.

[0127] Step 10715: Update the beacon detection network based on the pairing loss value.

[0128] In this embodiment, the pairing loss value can be substituted into optimization algorithms such as SGD (stochastic gradient descent) and Adam (Adaptive momentum), and the beacon detection network is back-propagated to update the parameters in the beacon detection network until the performance of the beacon detection network meets the requirements.

[0129] Step 1072: Input the first received signal strength indicator value of the candidate Bluetooth beacon signal into the beacon detection network to detect the quality value of the candidate Bluetooth beacon signal in positioning.

[0130] In this embodiment, the first received signal strength indicator value (sequence) of each candidate Bluetooth beacon signal is input into the beacon detection network, and the beacon detection network detects the quality value of the candidate Bluetooth beacon signal in positioning.

[0131] Step 1073: Filter out m candidate Bluetooth beacon signals with the highest quality values ​​to obtain a target beacon set.

[0132] In this embodiment, the quality values ​​of the candidate Bluetooth beacon signals are compared, and m candidate Bluetooth beacon signals with the highest quality values ​​are screened out and recorded as the target beacon set.

[0133] Step 1074: In the target beacon set, query the accuracy of using any n candidate Bluetooth beacon signals.

[0134] In this embodiment, the accuracy of combined positioning using n different base stations can be recorded by testing, user reporting and error correction, etc. Then, in the target beacon set, the accuracy of combined positioning using candidate Bluetooth beacon signals broadcast by any n corresponding base stations can be queried.

[0135] Wherein, m and n are both positive integers, and m is greater than n. For example, m is 6, n is 3, and so on.

[0136] For the test case, if the positioning deviation is within the preset threshold (such as 1 meter), it can be regarded as correct positioning. If the positioning deviation is outside the preset threshold (such as 1 meter), it can be regarded as wrong positioning, and the positioning accuracy is calculated accordingly.

[0137] For the case where the user reports an error correction, if the user does not report a positioning error, the positioning can be considered correct. If the user reports a positioning error, it can be considered a positioning error, and the positioning accuracy is calculated based on this.

[0138] Step 1075: Filter out n candidate Bluetooth beacon signals with the highest accuracy to obtain the target Bluetooth beacon signal.

[0139] The accuracies corresponding to the n candidate Bluetooth beacon signals are compared, and the n candidate Bluetooth beacon signals with the highest accuracy are screened out to obtain the target Bluetooth beacon signal.

[0140] This embodiment combines the real-time positioning quality value with the historical positioning accuracy, selects the target Bluetooth beacon signal from the aspects of real-time performance and stability, reduces the fluctuation of the target Bluetooth beacon signal as much as possible, improves the performance of the target Bluetooth beacon signal, and thus improves the accuracy of Bluetooth-based positioning.

[0141] Step 108: Position the target based on the target Bluetooth beacon signal to obtain target coordinate information.

[0142] In practical applications, the mobile terminal can be positioned based on the target Bluetooth beacon signal (especially RSSI) to obtain the target coordinate information.

[0143] Exemplarily, a relationship model may be obtained based on RSSI and distance modeling, and the first received signal strength indicator value of the target Bluetooth beacon signal in each frame may be substituted into the relationship model to obtain the distance between the mobile terminal and the base station.

[0144] The relationship model is as follows:

[0145] P(d) = P(d0)-10nlog 10 (d / d0);

[0146] Wherein, P(d) is the RSSI when the distance from the base station is d, P(d0) is the RSSI when the distance from the base station is d0, and n is the path loss index.

[0147] Using algorithms such as trilateral positioning, multilateral positioning or weighted centroid positioning, the target coordinate information of the mobile terminal is calculated based on the distance between the mobile terminal and each base station.

[0148] In this embodiment, an external original Bluetooth beacon signal, a wireless fidelity signal, and an internal acceleration signal are respectively received; a first signal sequence representing a changing trend of a first received signal strength indicator value is generated according to the original Bluetooth beacon signal; a second signal sequence representing a changing trend of a second received signal strength indicator value is generated according to the wireless fidelity signal; a third signal sequence representing a jitter state is generated according to the acceleration signal; a filter set is selected according to the first signal sequence, the second signal sequence, and the third signal sequence; the filter set contains one or more filtering algorithms; one or more filtering algorithms are called in turn to filter the original Bluetooth beacon signal to obtain a candidate Bluetooth beacon signal; a plurality of candidate Bluetooth beacon signals with the highest positioning quality values ​​are screened out according to the first received signal strength indicator value as target Bluetooth beacon signals; positioning is performed according to the target Bluetooth beacon signal to obtain target coordinate information. This embodiment comprehensively evaluates the environmental state and the own state from the RSSI of the Bluetooth beacon signal, the RSSI of the Wi-Fi signal and the acceleration signal, and selects a suitable filtering algorithm to filter the Bluetooth beacon signal. It has high flexibility, effectively improves the matching degree with the environmental state and the own state, improves the filtering effect, improves the performance of the Bluetooth beacon signal, and evaluates the quality of positioning based on the RSSI of the Bluetooth beacon signal, and can screen out Bluetooth beacon signals with higher quality for positioning, which can effectively improve the accuracy of Bluetooth-based positioning.

[0149] Embodiment 2

[0150] See also Figure 3 , shows a schematic diagram of the structure of a Bluetooth-based positioning device provided by Embodiment 2 of the present invention. Figure 3 As shown, the device comprises:

[0151] The signal receiving module 301 is used to receive the external original Bluetooth beacon signal, the wireless fidelity signal, and the internal acceleration signal respectively;

[0152] A first signal sequence generating module 302, configured to generate a first signal sequence representing a change trend of a first received signal strength indicator value according to the original Bluetooth beacon signal;

[0153] A second signal sequence generating module 303, configured to generate a second signal sequence representing a change trend of a second received signal strength indicator value according to the wireless fidelity signal;

[0154] A third signal sequence generating module 304, configured to generate a third signal sequence representing a shaking state according to the acceleration signal;

[0155] A filter set selection module 305, configured to select a filter set according to the first signal sequence, the second signal sequence and the third signal sequence; the filter set includes one or more filter algorithms;

[0156] A filtering processing module 306 is used to sequentially call one or more filtering algorithms to filter the original Bluetooth beacon signal to obtain a candidate Bluetooth beacon signal;

[0157] A beacon signal screening module 307, configured to screen out a plurality of candidate Bluetooth beacon signals with the highest positioning quality values ​​according to the first received signal strength indicator value as target Bluetooth beacon signals;

[0158] The Bluetooth positioning module 308 is used to perform positioning according to the target Bluetooth beacon signal to obtain target coordinate information.

[0159] In one embodiment of the present invention, the first signal sequence generating module 302 is further configured to:

[0160] Calculating an average value of the first received signal strength indicator value of the same original Bluetooth beacon signal to obtain a Bluetooth received signal strength indicator value;

[0161] For the plurality of Bluetooth beacon signals having the highest Bluetooth received signal strength indicator values, calculating an average value of the first received signal strength indicator values ​​at the same time to obtain a first co-located received signal strength indicator value;

[0162] For the plurality of Bluetooth beacon signals with the highest Bluetooth received signal strength indicator values, respectively counting minimum and maximum values ​​of the first received signal strength indicator values ​​at the same time to form a first co-location fluctuation amplitude;

[0163] The first co-located received signal strength indicator value at each moment and the first co-located fluctuation amplitude at each moment are combined into a first signal sequence representing a variation trend of the first received signal strength indicator value.

[0164] In one embodiment of the present invention, the second signal sequence generating module 303 is further configured to:

[0165] Counting the number of the wireless fidelity signals;

[0166] For each of the wireless fidelity signals, calculating an average of the second received signal strength indication values ​​at the same time to obtain a second co-located received signal strength indication value;

[0167] For each of the wireless fidelity signals, respectively, calculating minimum and maximum values ​​of the second received signal strength indicator values ​​at the same time to form a second co-location fluctuation amplitude;

[0168] Each of the numbers, the second co-located received signal strength indicator value at each moment, and the second co-located fluctuation amplitude at each moment are combined into a second signal sequence representing a change trend of the second received signal strength indicator value.

[0169] In one embodiment of the present invention, the third signal sequence generating module 304 is further configured to:

[0170] amplifying the acceleration signal in the Z direction;

[0171] At the same time, the acceleration signal amplified in the Z direction is added to the sum of the acceleration signal in the X direction and the acceleration signal in the Y direction to obtain a jitter value;

[0172] The jitter values ​​at various moments are combined into a third signal sequence representing the jitter state.

[0173] In one embodiment of the present invention, the filter set selection module 305 is further used to:

[0174] Determine a filtering classification network; the filtering classification network includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a fourth convolutional layer, a depth-separable convolutional layer and a fully connected layer;

[0175] Converting the first signal sequence into a first feature map, inputting the first feature map into the first convolution layer to sequentially perform convolution operations and activation operations to obtain Bluetooth beacon features;

[0176] Converting the second signal sequence into a second feature map, inputting the second feature map into the second convolutional layer to sequentially perform convolution operations and activation operations to obtain wireless fidelity features;

[0177] Converting the third signal sequence into a third feature map, inputting the third feature map into the third convolutional layer to sequentially perform convolution operations and activation operations to obtain a jitter feature;

[0178] fusing the Bluetooth beacon feature, the wireless fidelity feature, and the jitter feature into an original multimodal feature;

[0179] Inputting the original multimodal features into the depthwise separable convolutional layer to sequentially perform convolution operations and activation operations to obtain candidate multimodal features;

[0180] Inputting the candidate multimodal features into the fourth convolutional layer to perform a convolution operation to obtain a target multimodal feature;

[0181] Inputting the target multimodal features into the fully connected layer and mapping them into classification features;

[0182] Performing an activation operation on the classification features to obtain the probability of each filter set;

[0183] Output the filter set with the highest probability.

[0184] In one embodiment of the present invention, the beacon signal screening module 307 includes:

[0185] A beacon detection network determination module, used to determine a beacon detection network;

[0186] A quality value detection module, used for inputting the first received signal strength indicator value of the candidate Bluetooth beacon signal into the beacon detection network to detect the quality value of the candidate Bluetooth beacon signal in positioning;

[0187] A target beacon set screening module is used to screen out the m candidate Bluetooth beacon signals with the highest quality values ​​to obtain a target beacon set;

[0188] An accuracy query module, used to query the accuracy of using any n candidate Bluetooth beacon signals in the target beacon set; m and n are both positive integers, and m is greater than n;

[0189] The target Bluetooth beacon signal determination module is used to screen out the n candidate Bluetooth beacon signals with the highest accuracy to obtain the target Bluetooth beacon signal.

[0190] In one embodiment of the present invention, the beacon detection network determination module includes:

[0191] A sample set sampling module is used to sample any two frames of sample Bluetooth beacon signals as a sample set;

[0192] A quality label marking module, used to mark the sample set with a quality label according to the positioning accuracy of the sample Bluetooth beacon signal;

[0193] A forward processing module, used for inputting the third received signal strength indicator values ​​of the two frames of the sample Bluetooth beacon signals in the sample set into the beacon detection network to detect the quality value of the sample Bluetooth beacon signals in positioning;

[0194] A pairing loss value calculation module, used to generate a pairing loss value according to the quality value and the quality label;

[0195] A beacon detection network updating module is used to update the beacon detection network according to the pairing loss value.

[0196] In one embodiment of the present invention, the quality label marking module is further used to:

[0197] In the same scene, the two frames of sample Bluetooth beacon signals and n-1 frames of reference Bluetooth beacon signals are respectively combined into a test beacon set; the scene is configured with actual coordinate information;

[0198] Performing positioning according to each of the test beacon sets to obtain test coordinate information;

[0199] Calculate the difference between each of the actual coordinate information and the test coordinate information to obtain a single point positioning offset;

[0200] For each frame of the sample Bluetooth beacon signal, calculate the average value of the single point positioning offset to obtain the overall positioning offset;

[0201] The sample set is annotated with a quality label that the positioning accuracy of the sample Bluetooth beacon signal with a smaller overall positioning offset is better than the positioning accuracy of the sample Bluetooth beacon signal with a larger overall positioning offset.

[0202] The Bluetooth-based positioning device provided in the embodiment of the present invention can execute the Bluetooth-based positioning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the Bluetooth-based positioning method.

[0203] Embodiment 3

[0204] See also Figure 4 , showing a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0205] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0206] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0207] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a positioning method based on Bluetooth.

[0208] In some embodiments, the Bluetooth-based positioning method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the Bluetooth-based positioning method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the Bluetooth-based positioning method in any other appropriate manner (e.g., by means of firmware).

[0209] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0210] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0211] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0212] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0213] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0214] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0215] Embodiment 4

[0216] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the Bluetooth-based positioning method provided by any embodiment of the present invention is implemented.

[0217] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0218] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0219] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A positioning method based on Bluetooth, characterized in that: include: Respectively receive external original Bluetooth beacon signals, wireless fidelity signals, and internal acceleration signals; Generating a first signal sequence representing a change trend of a first received signal strength indicator value according to the original Bluetooth beacon signal; generating a second signal sequence representing a change trend of a second received signal strength indicator value according to the wireless fidelity signal; generating a third signal sequence representing a shaking state according to the acceleration signal; Selecting a filter set according to the first signal sequence, the second signal sequence and the third signal sequence; the filter set contains one or more filter algorithms; Calling one or more of the filtering algorithms in sequence to filter the original Bluetooth beacon signal to obtain a candidate Bluetooth beacon signal; Filtering, according to the first received signal strength indicator value, a plurality of the candidate Bluetooth beacon signals with the highest positioning quality values ​​as target Bluetooth beacon signals; Positioning is performed according to the target Bluetooth beacon signal to obtain target coordinate information.

2. The method according to claim 1, characterized in that The step of generating a first signal sequence representing a change trend of a first received signal strength indicator value according to the original Bluetooth beacon signal comprises: Calculating an average value of the first received signal strength indicator value of the same original Bluetooth beacon signal to obtain a Bluetooth received signal strength indicator value; For the plurality of Bluetooth beacon signals having the highest Bluetooth received signal strength indicator values, calculating an average value of the first received signal strength indicator values ​​at the same time to obtain a first co-located received signal strength indicator value; For the plurality of Bluetooth beacon signals with the highest Bluetooth received signal strength indicator values, respectively counting minimum and maximum values ​​of the first received signal strength indicator values ​​at the same time to form a first co-location fluctuation amplitude; The first co-located received signal strength indicator value at each moment and the first co-located fluctuation amplitude at each moment are combined into a first signal sequence representing a variation trend of the first received signal strength indicator value.

3. The method according to claim 2, characterized in that The generating, according to the wireless fidelity signal, a second signal sequence representing a change trend of a second received signal strength indicator value comprises: Counting the number of the wireless fidelity signals; For each of the wireless fidelity signals, calculating an average of the second received signal strength indication values ​​at the same time to obtain a second co-located received signal strength indication value; For each of the wireless fidelity signals, respectively, calculating minimum and maximum values ​​of the second received signal strength indicator values ​​at the same time to form a second co-location fluctuation amplitude; Each of the numbers, the second co-located received signal strength indicator value at each moment, and the second co-located fluctuation amplitude at each moment are combined into a second signal sequence representing a change trend of the second received signal strength indicator value.

4. The method according to claim 3, characterized in that The step of generating a third signal sequence representing a shaking state according to the acceleration signal comprises: amplifying the acceleration signal in the Z direction; At the same time, the acceleration signal amplified in the Z direction is added to the sum of the acceleration signal in the X direction and the acceleration signal in the Y direction to obtain a jitter value; The jitter values ​​at various moments are combined into a third signal sequence representing the jitter state.

5. The method according to claim 4, characterized in that The selecting a filter set according to the first signal sequence, the second signal sequence, and the third signal sequence comprises: Determine a filtering classification network; the filtering classification network includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a fourth convolutional layer, a depth-separable convolutional layer and a fully connected layer; Converting the first signal sequence into a first feature map, inputting the first feature map into the first convolution layer to sequentially perform convolution operations and activation operations to obtain Bluetooth beacon features; Converting the second signal sequence into a second feature map, inputting the second feature map into the second convolutional layer to sequentially perform convolution operations and activation operations to obtain wireless fidelity features; Converting the third signal sequence into a third feature map, inputting the third feature map into the third convolutional layer to sequentially perform convolution operations and activation operations to obtain a jitter feature; fusing the Bluetooth beacon feature, the wireless fidelity feature, and the jitter feature into an original multimodal feature; Inputting the original multimodal features into the depthwise separable convolutional layer to sequentially perform convolution operations and activation operations to obtain candidate multimodal features; Inputting the candidate multimodal features into the fourth convolutional layer to perform a convolution operation to obtain a target multimodal feature; Inputting the target multimodal features into the fully connected layer and mapping them into classification features; Performing an activation operation on the classification features to obtain the probability of each filter set; Output the filter set with the highest probability.

6. The method according to any one of claims 1 to 5, characterized in that The step of selecting, according to the first received signal strength indicator value, a plurality of candidate Bluetooth beacon signals having the highest positioning quality values ​​as target Bluetooth beacon signals includes: Determine the beacon detection network; Inputting the first received signal strength indicator value of the candidate Bluetooth beacon signal into the beacon detection network to detect the quality value of the candidate Bluetooth beacon signal in positioning; Filter out the m candidate Bluetooth beacon signals with the highest quality values ​​to obtain a target beacon set; In the target beacon set, query the accuracy of using any n candidate Bluetooth beacon signals; m and n are both positive integers, and m is greater than n; The n candidate Bluetooth beacon signals with the highest accuracy are screened out to obtain a target Bluetooth beacon signal.

7. The method according to claim 6, characterized in that The determining of the beacon detection network comprises: Sample any two frames of sample Bluetooth beacon signals as a sample set; Marking the sample set with a quality label according to the positioning accuracy of the sample Bluetooth beacon signal; Inputting the third received signal strength indicator values ​​of the two frames of the sample Bluetooth beacon signals in the sample set into the beacon detection network respectively to detect the quality values ​​of the sample Bluetooth beacon signals in positioning; generating a pairing loss value according to the quality value and the quality label; The beacon detection network is updated according to the pairing loss value.

8. The method according to claim 7, characterized in that The step of labeling the sample set with a quality tag according to the positioning accuracy of the sample Bluetooth beacon signal includes: In the same scene, the two frames of sample Bluetooth beacon signals and n-1 frames of reference Bluetooth beacon signals are respectively combined into a test beacon set; the scene is configured with actual coordinate information; Performing positioning according to each of the test beacon sets to obtain test coordinate information; Calculate the difference between each of the actual coordinate information and the test coordinate information to obtain a single point positioning offset; For each frame of the sample Bluetooth beacon signal, an average value of the single point positioning offset is calculated to obtain an overall positioning offset; The sample set is annotated with a quality label that the positioning accuracy of the sample Bluetooth beacon signal with a smaller overall positioning offset is better than the positioning accuracy of the sample Bluetooth beacon signal with a larger overall positioning offset.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the Bluetooth-based positioning method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the Bluetooth-based positioning method according to any one of claims 1 to 8 is implemented.

Images