A method, device, and storage medium for Bluetooth navigation in virtual reality

Abstract

The present invention discloses a method, device and storage medium for Bluetooth navigation in a virtual reality. The method includes: if a request to navigate to a destination in an indoor environment is received, then simultaneously collect multiple frames of image data and multiple frames of Bluetooth beacon signals in the indoor environment; determine whether the multiple frames of image data meet the conditions for indoor environment navigation; if so, extract target building features from the current frame of image data; extract multiple target Bluetooth beacon features from multiple received signal strength indications; fuse the target building features and the multiple target Bluetooth beacon features into target fingerprint features; detect the real-time position of the mobile device in the indoor environment according to the target fingerprint features; and display a virtual route from the real-time position to the destination in the form of virtual reality in the image data. When the indoor environment changes or there is interference, the influence on the features can be reduced, the positioning accuracy can be improved, and thus the accuracy of AR navigation can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of Bluetooth, and in particular, to a method, device, and storage medium for Bluetooth navigation in a virtual reality environment. Background Art

[0002] In large indoor venues such as shopping malls, in order to facilitate users to find their destinations, fingerprint technology based on the Bluetooth protocol is usually used for positioning and navigation.

[0003] In the offline stage, Bluetooth base stations (Beacons) are deployed in various target areas indoors to collect RSSI (Received Signal Strength Indication) data of Bluetooth beacon signals at different positions, forming a fingerprint database.

[0004] In the online stage, the user's device scans the surrounding Bluetooth beacon signals, and matches the real-time collected RSSI data with the fingerprint database to determine the user's location.

[0005] However, the indoor environment changes rapidly and there is a lot of interference, resulting in a certain difference between the online indoor environment and the offline indoor environment, reducing the positioning accuracy and thus the navigation accuracy. Summary of the Invention

[0006] In view of this, the present invention provides a method, device, and storage medium for Bluetooth navigation in a virtual reality environment to improve the positioning and navigation accuracy of fingerprint technology based on the Bluetooth protocol.

[0007] The first aspect of the present invention provides a method for Bluetooth navigation in a virtual reality environment, which is applied to a mobile device. The method includes:

[0008] If a request to navigate to a destination in an indoor environment is received, then collect multiple frames of image data and multiple frames of Bluetooth beacon signals simultaneously in the indoor environment; the Bluetooth beacon signals have received signal strength indications;

[0009] Determine whether the multiple frames of image data meet the conditions for navigation in the indoor environment; if so, extract target building features from the current frame of image data;

[0010] Extract multiple target Bluetooth beacon features from the multiple frames of received signal strength indications;

[0011] Fuse the target building features and the multiple target Bluetooth beacon features into target fingerprint features;

[0012] Detect the real-time position of the mobile device in the indoor environment according to the target fingerprint features;

[0013] In the image data, a virtual route from the real-time position to the destination is displayed in a virtual reality manner.

[0014] The second aspect of the present invention provides a device for Bluetooth navigation in virtual reality, which is applied to a mobile device. The device includes:

[0015] An environmental data acquisition module, configured to collect multiple frames of image data and multiple frames of Bluetooth beacon signals simultaneously in the indoor environment if a request for navigating to a destination in the indoor environment is received; the Bluetooth beacon signals have received signal strength indications.

[0016] A navigation condition judgment module, configured to judge whether multiple frames of the image data meet the conditions for navigation in the indoor environment; if so, call a building feature extraction module.

[0017] A building feature extraction module, configured to extract target building features from the current frame of the image data.

[0018] A Bluetooth beacon feature extraction module, configured to extract multiple target Bluetooth beacon features from multiple frames of the received signal strength indications.

[0019] A fingerprint feature fusion module, configured to fuse the target building features and multiple target Bluetooth beacon features into a target fingerprint feature.

[0020] A real-time position detection module, configured to detect the real-time position of the mobile device in the indoor environment based on the target fingerprint feature.

[0021] A virtual route display module, configured to display a virtual route from the real-time position to the destination in the image data in a virtual reality manner.

[0022] The third aspect of the present invention provides a mobile device, which includes:

[0023] At least one processor; and

[0024] A memory communicatively connected to the at least one processor; wherein,

[0025] The memory stores a computer program executable by the at least one processor. When the computer program is executed by the at least one processor, the at least one processor is enabled to execute the method for Bluetooth navigation in virtual reality as described in the first aspect above.

[0026] The fourth aspect of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for Bluetooth navigation in virtual reality as described in the first aspect above is implemented.

[0027] The fifth aspect of the present invention provides a computer program product, which includes a computer program that, when executed by a processor, implements the method for Bluetooth navigation in a virtual reality as described in the first aspect above.

[0028] In this embodiment, if a request to navigate to a destination in an indoor environment is received, multiple frames of image data and multiple frames of Bluetooth beacon signals are collected simultaneously in the indoor environment; the Bluetooth beacon signals have received signal strength indications; it is determined whether the multiple frames of image data meet the conditions for indoor environment navigation; if so, target building features are extracted from the current frame of image data; multiple target Bluetooth beacon features are extracted from the multiple received signal strength indications; the target building features and the multiple target Bluetooth beacon features are fused into target fingerprint features; the real-time position of the mobile device in the indoor environment is detected based on the target fingerprint features; and a virtual route from the real-time position to the destination is displayed in the image data in a virtual reality manner. In this embodiment, the features of the building in the image data are reused to enhance the features of the RSSI, increasing the amount of information of the features. When the indoor environment changes or there is interference, the impact on the features can be reduced, improving the positioning accuracy and thus the accuracy of AR navigation.

[0029] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used 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

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0031] Figure 1 is a flowchart of a method for Bluetooth navigation in a virtual reality provided in Embodiment 1 of the present invention.

[0032] Figure 2 is a schematic structural diagram of a building detection network provided in Embodiment 1 of the present invention.

[0033] Figure 3 is a schematic structural diagram of a convolutional module provided in Embodiment 1 of the present invention.

[0034] Figure 4 is a schematic structural diagram of a Bluetooth beacon detection network provided in Embodiment 1 of the present invention.

[0035] Figure 5 It is a schematic structural diagram of a multi-modal fusion network provided in Embodiment 1 of the present invention.

[0036] Figure 6 It is an example diagram of an AR navigation provided in Embodiment 1 of the present invention;

[0037] Figure 7 It is a schematic structural diagram of a device for performing Bluetooth navigation in virtual reality provided in Embodiment 2 of the present invention.

[0038] Figure 8 It is a schematic structural diagram of a mobile device provided in Embodiment 3 of the present invention. Detailed implementation manners

[0039] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0040] 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 do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can cover sequences other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0041] Embodiment 1

[0042] Refer to Figure 1 , which shows a flowchart of a method for performing Bluetooth navigation in virtual reality provided in Embodiment 1 of the present invention. This method can be executed by a device for performing Bluetooth navigation in virtual reality. The device for performing Bluetooth navigation in virtual reality can be implemented in the form of hardware and / or software, and the device for performing Bluetooth navigation in virtual reality can be applied to mobile devices, such as mobile phones, smart watches, smart glasses, and so on. As Figure 1 shown, this method includes:

[0043] Step 101: If a request to navigate to a destination in an indoor environment is received, then collect multiple frames of image data and multiple frames of Bluetooth beacon signals simultaneously in the indoor environment.

[0044] In practical applications, sensors such as cameras, Bluetooth modules, and gyroscopes are configured in mobile devices. Operating systems such as Android, iOS, and Harmony can be installed in mobile devices, and various application programs and their mini-programs can be installed in these operating systems. For example, mall mini-programs, map applications, games, social applications, shopping applications, and so on.

[0045] When the user arrives at an indoor environment such as a mall, start the application program or its mini-program on the mobile terminal, select the destination in the indoor environment, such as a store, toilet, elevator, etc., thereby triggering a request to navigate to the destination in the indoor environment. At this time, the application program or its mini-program can generate a prompt message to guide the user to stabilize the mobile device, reduce jitter, and face the camera towards the building.

[0046] Then, the application program or its mini-program can synchronously turn on the camera, Bluetooth module, and gyroscope, call the camera to collect multiple frames of image data, call the Bluetooth module to collect multiple frames of Bluetooth beacon signals, and call the gyroscope to collect multiple frames of angular velocity signals.

[0047] Among them, each frame of Bluetooth beacon signal has a Received Signal Strength Indicator (RSSI).

[0048] Step 102: Determine whether the multiple frames of image data meet the conditions for indoor navigation; if so, execute Step 103.

[0049] In this embodiment, an indoor navigation service based on AR (Augmented Reality) is provided for the user. However, the computing power of the mobile device is relatively limited. Factors such as the blurring of image data caused by jitter and the lack of building features caused by the user's improper handholding will affect the effect of indoor navigation. Therefore, the information of the image data itself or external information can be used to determine whether the multiple frames of image data meet the conditions for indoor navigation, while ensuring the user experience and reducing the consumption of resources of the mobile device.

[0050] When the conditions for indoor navigation are met, an indoor navigation service based on AR is provided on the basis of the multiple frames of image data.

[0051] When the conditions for indoor navigation are not met, the indoor navigation service based on AR can be paused, and the user can be prompted to adjust the mobile device so as to meet the conditions for indoor navigation.

[0052] In a specific implementation, the angular velocity signal recorded when collecting each frame of image data can be queried, and the angular velocity signal is processed by Kalman filtering to obtain the attitude of the mobile device.

[0053] Among them, the attitude of the mobile device can be represented by a quaternion, that is, four parameters are used to represent rotation.

[0054] Taking the Extended Kalman Filter (EKF) as an example, the steps of EKF include the following two stages:

[0055] 1. Prediction stage: Using the attitude (estimated value) at the previous moment and the system model, predict the attitude at the current moment.

[0056] 2. Update stage: Using the angular velocity signal (measured value) of the gyroscope at the current moment, update the attitude (estimated value).

[0057] Among them, the system model for calculating the attitude of the device can be expressed as: x k = f(x k-1 , u k ) + w k , z k = h(x k ) + v k .

[0058] Among them, x k is the attitude at time k, f(x k-1 , u k ) is the state transition function, which describes the change relationship from the attitude x k-1 at the previous moment to the attitude x k at the current moment, u k is the angular velocity signal of the gyroscope, w k is the process noise, representing the random error in the state transition process, z k is the angular velocity signal (measured value) of the gyroscope at time k.

[0059] h(x k ) is the measurement function, which describes the corresponding relationship between the attitude x k at the current moment and the angular velocity signal (measured value) z k of the gyroscope, v k is the measurement noise, representing the random error in the gyroscope measurement process.

[0060] Furthermore, when performing EKF processing on the angular velocity signal, the following steps are included:

[0061] S1. Initialization: Initialize the state estimate value x0 and the covariance matrix P0.

[0062] S2. Prediction stage: Use the state transition function f(x k-1 , u k ) to calculate the predicted state x hat {k|k - 1}; Use the Jacobian matrix F of the state transition function k to calculate the predicted covariance matrix P hat {k|k - 1}.

[0063] S3. Update stage: Calculate the Kalman gain K k ; Use the measurement function h(x k ) and the measurement value z k to calculate the measurement residual; Update the state estimate value x hat {k|k}; Update the covariance matrix P{k|k}.

[0064] Calculate the difference between the attitude at the current moment and the attitude at the previous moment to obtain the offset amplitude at the current moment.

[0065] Compare the attitude at the current moment with the preset range, and compare the movement amplitude at the current moment with the preset first threshold, where the range represents that the attitude of the mobile phone is that the camera is horizontal and in the forward shooting state, not the upward or downward shooting state. In this way, the image data contains more features of buildings (such as roads, stores, etc.). The first threshold is used to divide the jitter state of the mobile device. When it is less than or equal to the first threshold, the jitter state of the mobile device is lower and the image data is clearer. When it is greater than the first threshold, the jitter state of the mobile device is higher and the image data is more blurred.

[0066] If the currently collected attitude is within the preset range and the offset amplitude is less than or equal to the preset first threshold, it is determined that the current frame of image data meets the conditions for indoor environment navigation.

[0067] If the currently collected attitude is outside the preset range and / or the offset amplitude is greater than the preset first threshold, it is determined that the current frame of image data does not meet the conditions for indoor environment navigation.

[0068] Step 103. Extract the target building features from the current frame of image data.

[0069] In practical applications, deep learning technology or machine learning technology can be used to extract the features of surrounding buildings from the current frame of image data, denoted as target building features.

[0070] In indoor environments such as shopping malls, the degree of commercialization is relatively high, and the degree of differentiation in the decoration of each building (such as stores) is relatively large, making the features of the buildings can be used as auxiliary anchor points for positioning.

[0071] In a specific implementation, a building detection network can be loaded for operation. Among them, the building detection network is trained using a semantic segmentation mode, enabling the building detection network to have the ability to extract target building features from image data.

[0072] During semantic segmentation training, the building detection network is used as the encoder, and a decoder is configured for it. The encoder is responsible for extracting target building features from image data, and the decoder is responsible for identifying the semantics (building or non-building) of each pixel point based on the target building. The encoder (i.e., the building detection network) and the decoder are updated according to the loss value (such as cross-entropy, Dice loss, etc.) between the image data and the semantics. When the training is completed, the decoder is discarded, and the encoder (i.e., the building detection network) is retained.

[0073] As Figure 2 shown, the building detection network includes a first convolutional module ConvModule_1, a second convolutional module ConvModule_2, a third convolutional module ConvModule_3, and a spatial pyramid pooling layer (Spatial Pyramid Pooling, SPP).

[0074] Furthermore, as Figure 3 shown, the first convolutional module ConvModule_1, the second convolutional module ConvModule_2, and the third convolutional module ConvModule_3 all sequentially include a convolutional layer (Convolutional Layer, Conv), a batch normalization layer (Batch Normalization, BN), and a rectified linear unit layer (Rectified Linear Unit, ReLU). The convolutional layer can provide convolutional operations, the batch normalization layer can provide normalization operations, and the rectified linear unit layer can provide activation operations.

[0075] Input the current frame image data into the first convolutional module ConvModule_1 for processing (i.e., sequentially perform convolutional operations, normalization operations, and activation operations), and extract the first candidate building features from the current frame image data.

[0076] Input the first candidate building features into the second convolutional module ConvModule_2 for processing (i.e., sequentially perform convolutional operations, normalization operations, and activation operations), and extract the second candidate building features from the first candidate building features.

[0077] Use the Concatnate function to concatenate the first candidate building features and the second candidate building features into the third candidate building features.

[0078] Input the third candidate building feature into the third convolutional module ConvModule_3 for processing (i.e., sequentially perform convolution operation, normalization operation, and activation operation) to extract the fourth candidate building feature from the third candidate building feature.

[0079] Input the fourth candidate building feature into the spatial pyramid pooling layer SPP to perform pooling operation to obtain the target building feature.

[0080] Step 104: Extract various target Bluetooth beacon features from multiple frames of received signal strength indications.

[0081] In practical applications, deep learning techniques or machine learning techniques can be used to extract features of itself in different dimensions from multiple frames of received signal strength indications to obtain various target Bluetooth beacon features.

[0082] The target Bluetooth beacon features of multiple RSSIs can increase the information content of the features, improve the differentiation of RSSI features, and enable the target Bluetooth beacon features of RSSI to be used as the main anchor points for positioning.

[0083] In an embodiment of the present invention, the target Bluetooth beacon features include target beacon classification features and target beacon enhancement features. Then, in this embodiment, step 104 may include the following steps:

[0084] Step 1041: Load the Bluetooth beacon detection network.

[0085] In this embodiment, the Bluetooth beacon detection network can be loaded and run. Among them, the Bluetooth beacon detection network is trained in a classification mode so that the Bluetooth beacon detection network has the ability to extract various target Bluetooth beacon features from multiple frames of received signal strength indications.

[0086] Among them, as Figure 4 shown, the Bluetooth beacon detection network includes a first encoder Encoder_1, a second encoder Encoder_2, and a decoder Decoder. The first encoder Encoder_1 is responsible for extracting features from multiple frames of received signal strength indications from the perspective of multi-classification of base stations. The second encoder Encoder_2 is responsible for extracting features from multiple frames of received signal strength indications from the perspective of binary classification of the base station range, so as to enhance the features of the first encoder Encoder_1. The decoder Decoder is responsible for integrating the features of the first encoder Encoder_1 and the second encoder Encoder_2.

[0087] During classification training, a first fully connected layer is cascaded after the second encoder Encoder_2, and a second fully connected layer is cascaded after the decoder Decoder to form a beacon classification network.

[0088] The first fully-connected layer is responsible for binary classification of the features of the second encoder Encoder_2 (i.e., whether the base station to which the Bluetooth beacon signal belongs is within the range formed by a specified radius centered on the mobile device), and generates a first loss value (such as cross entropy, etc.) based on the classification result of the first fully-connected layer.

[0089] The second fully-connected layer is responsible for multi-classification of the features in the decoder Decoder (i.e., detecting the base station to which the Bluetooth beacon signal belongs), and generates a second loss value (such as cross entropy, etc.) based on the classification result of the second fully-connected layer.

[0090] The first loss value and the second loss value are linearly fused into a third loss value, and the beacon classification network is updated based on the third loss value. When the training is completed, the first fully-connected layer and the second fully-connected layer are discarded, and the first encoder Encoder_1, the second encoder Encoder_2, and the decoder Decoder are retained.

[0091] Step 1042: Input multiple frames of received signal strength indications into the first encoder for encoding into target beacon classification features.

[0092] In this embodiment, as Figure 4 shown, starting from the current moment, screen out the RSSIs of T (T is a positive integer) frames of Bluetooth beacon signals and input them into the first encoder Encoder_1 for encoding into target beacon classification features, where the target beacon classification features are used to detect the base station to which the Bluetooth beacon signal belongs.

[0093] In a specific implementation, as Figure 4 shown, the first encoder Encoder_1 includes a first time-delay neural network TDNN_1, a fourth convolutional module ConvModule_4, and a fifth convolutional module ConvModule_5.

[0094] Among them, the first time-delay neural network TDNN_1 belongs to a time-delay neural network (Time Delay Neural Network, TDNN). It introduces multiple delayed RSSIs at each time step, and these delayed RSSIs are combined together to form new features, which can capture the correlation of RSSIs at different time points.

[0095] As Figure 3 shown, both the fourth convolutional module ConvModule_4 and the fifth convolutional module ConvModule_5 sequentially include a convolutional layer Conv, a batch normalization layer BN, and a rectified linear unit layer ReLU.

[0096] Then, input multiple frames of received signal strength indication RSSIs into the first time-delay neural network TDNN_1 to convert them into three-dimensional first candidate beacon classification features.

[0097] Input the first candidate beacon classification feature into the fourth convolutional module ConvModule_4 for processing (i.e., sequentially perform convolutional operation, normalization operation, and activation operation) to extract the second candidate beacon classification feature from the first candidate beacon classification feature.

[0098] Input the second candidate beacon classification feature into the fifth convolutional module ConvModule_5 for processing (i.e., sequentially perform convolutional operation, normalization operation, and activation operation) to extract the target beacon classification feature from the second candidate beacon classification feature.

[0099] Step 1043: Input the multi-frame received signal strength indication into the second encoder to encode it into the target beacon range feature.

[0100] In this embodiment, as Figure 4 shown, starting from the current moment, filter out the RSSI of T (T is a positive integer) frames of Bluetooth beacon signals and input it into the second encoder Encoder_2 to encode it into the target beacon range feature, and the target beacon range feature is used to detect whether the base station to which the Bluetooth beacon signal belongs is within the range formed by a specified radius centered on the mobile device.

[0101] Generally, the RSSI of Bluetooth beacon signals with relatively short distance and strong signal is used for positioning. However, in a real-time indoor environment, there are interferences from wireless signals such as WiFi (Wireless Fidelity), which causes fluctuations in the RSSI of Bluetooth beacon signals. In this embodiment, a set of features is constructed for whether the RSSI of Bluetooth beacon signals is within the surrounding range. This set of features is relatively simple and has strong stability, and can achieve an activation effect (i.e., enhance the features of the RSSI of Bluetooth beacon signals in the surrounding range and suppress the features of the RSSI of Bluetooth beacon signals in the distant range), enhance the features of the original RSSI of Bluetooth beacon signals used for classification, and enhance the robustness.

[0102] In specific implementation, as Figure 4 shown, the second encoder Encoder_2 includes the second time-delay neural network TDNN_2, the sixth convolutional module ConvModule_6, and the seventh convolutional module ConvModule_7.

[0103] Among them, as Figure 3 shown, both the sixth convolutional module ConvModule_6 and the seventh convolutional module ConvModule_7 sequentially include a convolutional layer Conv, a batch normalization layer BN, and a rectified linear unit layer ReLU.

[0104] Then, input the multi-frame received signal strength indication RSSI into the second time-delay neural network TDNN_2 to convert it into a three-dimensional first candidate beacon range feature.

[0105] Input the first candidate beacon range feature into the sixth convolutional module ConvModule_6 for processing (i.e., sequentially perform convolutional operation, normalization operation, and activation operation) to extract the second candidate beacon range feature from the first candidate beacon range feature.

[0106] Input the second candidate beacon range feature into the seventh convolutional module ConvModule_7 for processing (i.e., sequentially perform convolutional operation, normalization operation, and activation operation) to extract the target beacon range feature from the second candidate beacon range feature.

[0107] Step 1044: Concatenate the target beacon classification feature and the target beacon range feature into a beacon fusion feature.

[0108] In this embodiment, the Concatnate function can be used to concatenate the target beacon classification feature and the target beacon range feature into a beacon fusion feature.

[0109] Step 1045: Input the beacon fusion feature into the decoder to decode it into a target beacon enhanced feature.

[0110] In this embodiment, as Figure 4 shown, input the beacon fusion feature into the decoder Encoder for decoding to obtain the target beacon enhanced feature.

[0111] In specific implementation, as Figure 4 shown, the decoder Encoder includes an eighth convolutional module ConvModule_8 and a multi-head attention module (Multi Head Attention, MHA).

[0112] Among them, as Figure 3 shown, the eighth convolutional module ConvModule_8 sequentially includes a convolutional layer Conv, a batch normalization layer BN, and a rectified linear unit layer ReLU.

[0113] Then, input the beacon fusion feature into the eighth convolutional module ConvModule_8 for processing (i.e., sequentially perform convolutional operation, normalization operation, and activation operation) to extract a candidate beacon enhanced feature from the beacon fusion feature.

[0114] Input the candidate beacon enhanced feature into the multi-head attention module MHA to fuse context information for the candidate beacon enhanced feature to extract the target beacon enhanced feature.

[0115] Step 105: Fuse the target building feature and multiple target Bluetooth beacon features into a target fingerprint feature.

[0116] In practical applications, deep learning techniques or machine learning techniques can be used to fuse the target building feature and multiple target Bluetooth beacon features to obtain the target fingerprint feature.

[0117] In a specific implementation, a multi-modal fusion network can be loaded for operation. The multi-modal fusion network is trained using a classification mode, enabling the multi-modal fusion network to have the ability to fuse target building features and various target Bluetooth beacon features into target fingerprint features.

[0118] During classification training, a fully connected layer is cascaded after the multi-modal fusion network to form a fingerprint classification network. The fully connected layer is responsible for multi-classifying the features of the multi-modal fusion network (i.e., detecting the categories of target fingerprint features), generating a loss value (such as cross-entropy, etc.) based on the classification results of the fully connected layer, and updating the fingerprint classification network according to the loss value. When the training is completed, the fully connected layer is discarded, and the multi-modal fusion network is retained.

[0119] When building a fingerprint database offline, image data can be collected at the same location facing different angles, or panoramic image data can be collected using devices such as fisheye cameras. Image data of multiple regions are cropped from the panoramic image data, that is, multiple groups of image data can be formed at the same location. In this embodiment, the building detection network, the Bluetooth beacon detection network, and the multi-modal fusion network are decoupled, that is, the structures are separated and trained independently, enabling the building detection network to independently output the features of each group of image data, and the features of the RSSI output by the Bluetooth beacon detection network can be fused with the features of any group of image data into fingerprints in the multi-modal fusion network, improving the flexibility of fingerprint modeling.

[0120] The feature engineering of image data and the feature engineering of RSSI can be executed in parallel, and the execution frequency is adjusted according to the confidence levels of image data and RSSI for positioning, which can effectively improve the real-time performance.

[0121] In an indoor environment such as a shopping mall, if a certain building (such as a store) is redecorated, image data will be re-collected near the building, and the fingerprint database can be updated, effectively reducing the maintenance cost of the fingerprint database.

[0122] Among them, as Figure 5 shown, the multi-modal fusion network includes a first self-attention module Self-Atteintion_1 and a second self-attention module Self-Atteintion_2.

[0123] Then, the Concatnate function can be used to splice the target building feature E1 and the target beacon classification feature E2 into a first candidate fingerprint feature.

[0124] The first candidate fingerprint feature is input into the first self-attention module Self-Atteintion_1 to extract a second candidate fingerprint feature.

[0125] The Add function can be used to add the second candidate fingerprint feature to the target beacon enhancement feature E3 to obtain the third candidate fingerprint feature.

[0126] The third candidate fingerprint feature is input into the second self-attention module Self-Atteintion_2 to extract the target fingerprint feature.

[0127] On the one hand, RSSI belongs to a long time series. The self-attention mechanism Self-Atteintion can capture long-distance dependencies to better model the global information in multi-modal data (i.e., the features of the building and the features of RSSI).

[0128] On the other hand, buildings with different structures block Bluetooth beacon signals. Therefore, the features of the building (i.e., the target building features) can not only be used as auxiliary anchors for positioning but also enhance the features of RSSI (i.e., various target Bluetooth beacon features).

[0129] The self-attention mechanism Self-Atteintion is used to capture the dependencies between the building and RSSI, dynamically classify the weights of the features of the building and RSSI, so as to fuse high-quality features and enhance the robustness of the system.

[0130] Step 106: Detect the real-time position of the mobile device in the indoor environment based on the target fingerprint feature.

[0131] In this embodiment, the target fingerprint feature can be used for positioning to detect the real-time position of the mobile device in the indoor environment.

[0132] In a specific implementation, a fingerprint library configured for the indoor environment is loaded; the fingerprint library has reference fingerprint features defined at various reference positions in the indoor environment, and the method of constructing the reference fingerprint features is the same as that of constructing the target fingerprint features.

[0133] At this time, the similarity between the target fingerprint feature and each reference fingerprint feature is calculated, such as cosine similarity, etc.

[0134] The similarities of each reference fingerprint feature are compared. If the similarity of a certain reference fingerprint feature is the highest, the reference position corresponding to the reference fingerprint feature is marked as the real-time position of the mobile device in the indoor environment.

[0135] Step 107: Display the virtual route from the real-time position to the destination in the form of virtual reality in the image data.

[0136] When determining the real-time position of a user in an indoor environment, algorithms such as the A* algorithm and the Dijkstra algorithm can be used to plan the optimal path from the real-time position to the destination, and the SLAM (Simultaneous Localization and Mapping) technology is used to align the coordinates of this path with the real environment (i.e., the content of the image data). As Figure 6 shown, according to the perspective of the camera and the position of the user, project this path onto the plane of the image data, represent this path with geometric figures 601 (such as arrows, line segments), etc., and supplement it with dynamic effects (such as arrow flashing, etc.) and navigation prompt information 602 (such as "turn left", "go straight", etc.), so as to generate a virtual route and realize AR navigation.

[0137] In specific implementation, the offset amplitude can be compared with a preset second threshold, where the second threshold is less than the first threshold.

[0138] If the offset amplitude is greater than the preset second threshold, it means that there is a certain jitter in the mobile device, which has a certain impact on AR navigation. Then calculate the difference between the current pose and the previous pose to obtain the offset direction.

[0139] Load the view window View in the current frame of image data.

[0140] Play the switching animation of the virtual route in the view window in a virtual reality manner along the offset direction to achieve a smooth transition of the virtual route and improve the user experience.

[0141] If the switching animation ends, then display the virtual route from the real-time position to the destination in the view window in a virtual reality manner.

[0142] In this embodiment, if a request to navigate to a destination in an indoor environment is received, then multiple frames of image data and multiple frames of Bluetooth beacon signals are collected simultaneously in the indoor environment; the Bluetooth beacon signals have a received signal strength indication; determine whether the multiple frames of image data meet the conditions for indoor environment navigation; if so, extract the target building features from the current frame of image data; extract multiple target Bluetooth beacon features from the multiple received signal strength indications; fuse the target building features and the multiple target Bluetooth beacon features into target fingerprint features; detect the real-time position of the mobile device in the indoor environment based on the target fingerprint features; display the virtual route from the real-time position to the destination in the image data in a virtual reality manner. This embodiment multiplexes the features of the building in the image data to enhance the features of the RSSI, increases the information content of the features, and can reduce the impact on the features when the indoor environment changes or there is interference, which can improve the positioning accuracy and thus improve the accuracy of AR navigation.

[0143] Embodiment Two

[0144] See Figure 7, showing a schematic structural diagram of a device for Bluetooth navigation in a virtual reality provided in the second embodiment of the present invention. As Figure 7 shown, applied to a mobile device, the device includes:

[0145] An environmental data acquisition module 701, configured to, if a request for navigating to a destination in an indoor environment is received, simultaneously acquire multiple frames of image data and multiple frames of Bluetooth beacon signals in the indoor environment; the Bluetooth beacon signals have received signal strength indications;

[0146] A navigation condition determination module 702, configured to determine whether multiple frames of the image data meet the conditions for navigation in the indoor environment; if so, call a building feature extraction module 703;

[0147] A building feature extraction module 703, configured to extract target building features from the current frame of the image data;

[0148] A Bluetooth beacon feature extraction module 704, configured to extract multiple target Bluetooth beacon features from multiple frames of the received signal strength indications;

[0149] A fingerprint feature fusion module 705, configured to fuse the target building features and the multiple target Bluetooth beacon features into target fingerprint features;

[0150] A real-time position detection module 706, configured to detect the real-time position of the mobile device in the indoor environment according to the target fingerprint features;

[0151] A virtual route display module 707, configured to display a virtual route from the real-time position to the destination in a virtual reality manner in the image data.

[0152] In an embodiment of the present invention, the navigation condition determination module 702 is further configured to:

[0153] Query the angular velocity signals recorded when each frame of the image data is acquired;

[0154] Perform Kalman filtering processing on the angular velocity signals to obtain the attitude of the mobile device;

[0155] Calculate the difference between the currently acquired attitude and the previous attitude to obtain an offset amplitude;

[0156] If the currently acquired attitude is within a preset range and the offset amplitude is less than or equal to a preset first threshold, it is determined that the current frame of the image data meets the conditions for navigation in the indoor environment;

[0157] If the currently collected attitude is outside a preset range and / or the offset amplitude is greater than a preset first threshold, it is determined that the image data of the current frame does not meet the conditions for navigation in the indoor environment;

[0158] The virtual route display module 707 is further configured to:

[0159] If the offset amplitude is greater than a preset second threshold, calculate the difference between the current attitude and the previous attitude to obtain the offset direction; the second threshold is less than the first threshold;

[0160] Load a view window in the image data of the current frame;

[0161] Play a switching animation of the virtual route in the view window in a virtual reality manner along the offset direction;

[0162] If the switching animation ends, display the virtual route from the real-time position to the destination in the view window in a virtual reality manner.

[0163] In an embodiment of the present invention, the building feature extraction module 703 is further configured to:

[0164] Load a building detection network; the building detection network includes a first convolutional module, a second convolutional module, a third convolutional module, and a spatial pyramid pooling layer; the first convolutional module, the second convolutional module, and the third convolutional module each sequentially include a convolutional layer, a batch normalization layer, and a rectified linear unit layer;

[0165] Input the image data of the current frame into the first convolutional module to extract first candidate building features;

[0166] Input the first candidate building features into the second convolutional module to extract second candidate building features;

[0167] Concatenate the first candidate building features and the second candidate building features into third candidate building features;

[0168] Input the third candidate building features into the third convolutional module to extract fourth candidate building features;

[0169] Input the fourth candidate building features into the spatial pyramid pooling layer to perform a pooling operation to obtain target building features.

[0170] In an embodiment of the present invention, the target Bluetooth beacon feature includes a target beacon classification feature and a target beacon enhancement feature;

[0171] The Bluetooth beacon feature extraction module 704 is further configured to:

[0172] Load the Bluetooth beacon detection network; the Bluetooth beacon detection network includes a first encoder, a second encoder, and a decoder;

[0173] Input multiple frames of the received signal strength indication into the first encoder to be encoded into target beacon classification features; the target beacon classification features are used to detect the base station to which the Bluetooth beacon signal belongs;

[0174] Input multiple frames of the received signal strength indication into the second encoder to be encoded into target beacon range features; the target beacon range features are used to detect whether the base station to which the Bluetooth beacon signal belongs is within a range formed by a specified radius centered on the mobile device;

[0175] Concatenate the target beacon classification features and the target beacon range features into beacon fusion features;

[0176] Input the beacon fusion features into the decoder to be decoded into target beacon enhancement features.

[0177] In an embodiment of the present invention, the first encoder includes a first time-delay neural network, a fourth convolutional module, and a fifth convolutional module, and the second encoder includes a second time-delay neural network, a sixth convolutional module, and a seventh convolutional module; the fourth convolutional module, the fifth convolutional module, the sixth convolutional module, and the seventh convolutional module each sequentially include a convolutional layer, a batch normalization layer, and a rectified linear unit layer;

[0178] The Bluetooth beacon feature extraction module 704 is further configured to:

[0179] Input multiple frames of the received signal strength indication into the first time-delay neural network to be converted into three-dimensional first candidate beacon classification features;

[0180] Input the first candidate beacon classification features into the fourth convolutional module to extract second candidate beacon classification features;

[0181] Input the second candidate beacon classification features into the fifth convolutional module to extract target beacon classification features;

[0182] The Bluetooth beacon feature extraction module 704 is further configured to:

[0183] Input multiple frames of the received signal strength indication into the second time-delay neural network to be converted into three-dimensional first candidate beacon range features;

[0184] Input the first candidate beacon range features into the sixth convolutional module to extract second candidate beacon range features;

[0185] Input the second candidate beacon range features into the seventh convolutional module to extract target beacon range features.

[0186] In one embodiment of the present invention, the decoder includes an eighth convolutional module and a multi-head attention module; the eighth convolutional module sequentially includes a convolutional layer, a batch normalization layer, and a rectified linear unit layer;

[0187] The Bluetooth beacon feature extraction module 704 is further configured to:

[0188] Input the beacon fusion feature into the eighth convolutional module to extract a candidate beacon enhanced feature;

[0189] Input the candidate beacon enhanced feature into the multi-head attention module to extract a target beacon enhanced feature.

[0190] In one embodiment of the present invention, the fingerprint feature fusion module 705 is further configured to:

[0191] Load a multi-modal fusion network; the multi-modal fusion network includes a first self-attention module and a second self-attention module;

[0192] Concatenate the target building feature and the target beacon classification feature into a first candidate fingerprint feature;

[0193] Input the first candidate fingerprint feature into the first self-attention module to extract a second candidate fingerprint feature;

[0194] Add the second candidate fingerprint feature and the target beacon enhanced feature to obtain a third candidate fingerprint feature;

[0195] Input the third candidate fingerprint feature into the second self-attention module to extract a target fingerprint feature.

[0196] In one embodiment of the present invention, the real-time position detection module 706 is further configured to:

[0197] Load a fingerprint database configured for the indoor environment; the fingerprint database has reference fingerprint features defined at various reference positions within the indoor environment;

[0198] Calculate the similarity between the target fingerprint feature and each of the reference fingerprint features;

[0199] If the similarity of a certain reference fingerprint feature is the highest, then mark the reference position corresponding to the reference fingerprint feature as the real-time position of the mobile device in the indoor environment.

[0200] The device for Bluetooth navigation in virtual reality provided by the embodiments of the present invention can execute the method for Bluetooth navigation in virtual reality provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method for Bluetooth navigation in virtual reality.

[0201] Embodiment 3

[0202] Refer to Figure 8 , which shows a schematic structural diagram of a mobile device provided by an embodiment of the present invention. The mobile device is intended to represent various forms of digital computers, such as, personal digital assistants, 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.

[0203] As Figure 8 shown, the mobile device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. 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 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the mobile 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.

[0204] Multiple components in the mobile 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 magnetic 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 mobile device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0205] The processor 11 can be various general-purpose and / or special-purpose 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 dedicated 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 the method of performing Bluetooth navigation in virtual reality.

[0206] In some embodiments, a method for Bluetooth navigation in virtual reality can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the mobile 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 method for Bluetooth navigation in virtual reality described above can be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for Bluetooth navigation in virtual reality by any other suitable means (e.g., by means of firmware).

[0207] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on a chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments 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 receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0208] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that when the computer programs are executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0209] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0210] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a mobile 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 a trackball) by which the user can provide input to the mobile device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0211] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0212] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0213] Embodiment 4

[0214] The embodiment of the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the method of Bluetooth navigation in virtual reality provided in any embodiment of the present invention.

[0215] In the process of implementing the computer program product, computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely 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, by using an Internet service provider to connect through the Internet).

[0216] It should be understood that various forms of the processes shown above can be used, reordering, adding or deleting steps. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. No limitation is made herein.

[0217] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for Bluetooth navigation in virtual reality, characterized in that, Applied to a mobile device, the method includes: If a request to navigate to a destination in an indoor environment is received, then collect multiple frames of image data and multiple frames of Bluetooth beacon signals simultaneously in the indoor environment; the Bluetooth beacon signals have received signal strength indications; Determine whether the multiple frames of image data meet the conditions for navigation in the indoor environment; if so, load a building detection network; the building detection network includes a first convolutional module, a second convolutional module, a third convolutional module, and a spatial pyramid pooling layer; Input the current frame of image data into the first convolutional module to extract a first candidate building feature; Input the first candidate building feature into the second convolutional module to extract a second candidate building feature; Concatenate the first candidate building feature and the second candidate building feature into a third candidate building feature; Input the third candidate building feature into the third convolutional module to extract a fourth candidate building feature; Input the fourth candidate building feature into the spatial pyramid pooling layer to perform a pooling operation to obtain a target building feature to represent the features of surrounding buildings; Load a Bluetooth beacon detection network; the Bluetooth beacon detection network includes a first encoder, a second encoder, and a decoder; Input the multiple frames of received signal strength indications into the first encoder to encode them into a target beacon classification feature; the target beacon classification feature is used to detect the base station to which the Bluetooth beacon signal belongs; Input the multiple frames of received signal strength indications into the second encoder to encode them into a target beacon range feature; the target beacon range feature is used to detect whether the base station to which the Bluetooth beacon signal belongs is within a range formed by a specified radius centered on the mobile device; Concatenate the target beacon classification feature and the target beacon range feature into a beacon fusion feature; Input the beacon fusion feature into the decoder to decode it into a target beacon enhancement feature; Load a multimodal fusion network; the multimodal fusion network includes a first self-attention module and a second self-attention module; Concatenate the target building feature and the target beacon classification feature into a first candidate fingerprint feature; Input the first candidate fingerprint feature into the first self-attention module to extract a second candidate fingerprint feature; Add the second candidate fingerprint feature and the target beacon enhancement feature to obtain a third candidate fingerprint feature; Input the third candidate fingerprint feature into the second self-attention module to extract a target fingerprint feature; Detect the real-time position of the mobile device in the indoor environment based on the target fingerprint feature; Display a virtual route from the real-time position to the destination in a virtual reality manner in the image data.

2. The method according to claim 1, wherein The determination of whether the multiple frames of image data meet the conditions for navigation in the indoor environment includes: Query the angular velocity signal recorded when each frame of image data is collected; Perform Kalman filtering on the angular velocity signal to obtain the attitude of the mobile device; Calculate the difference between the currently collected attitude and the previous attitude to obtain an offset amplitude; If the currently acquired attitude is within a preset range and the offset amplitude is less than or equal to a preset first threshold, it is determined that the image data of the current frame meets the conditions for navigation in the indoor environment; If the currently acquired attitude is outside the preset range and / or the offset amplitude is greater than the preset first threshold, it is determined that the image data of the current frame does not meet the conditions for navigation in the indoor environment; The virtual route from the real-time position to the destination is displayed in a virtual reality manner in the image data, including: If the offset amplitude is greater than a preset second threshold, calculate the difference between the current attitude and the previous attitude to obtain the offset direction; the second threshold is less than the first threshold; Load a view window in the image data of the current frame; Play a switching animation of the virtual route along the offset direction in the view window in a virtual reality manner; If the switching animation ends, display the virtual route from the real-time position to the destination in the view window in a virtual reality manner.

3. The method according to claim 1, wherein The first convolutional module, the second convolutional module, and the third convolutional module each sequentially include a convolutional layer, a batch normalization layer, and a rectified linear unit layer.

4. The method according to claim 1, characterized in that, The first encoder includes a first time-delay neural network, a fourth convolutional module, and a fifth convolutional module, and the second encoder includes a second time-delay neural network, a sixth convolutional module, and a seventh convolutional module; the fourth convolutional module, the fifth convolutional module, the sixth convolutional module, and the seventh convolutional module each sequentially include a convolutional layer, a batch normalization layer, and a rectified linear unit layer; Encoding the multi-frame received signal strength indication into a target beacon classification feature by inputting it into the first encoder includes: Inputting the multi-frame received signal strength indication into the first time-delay neural network to convert it into a three-dimensional first candidate beacon classification feature; Inputting the first candidate beacon classification feature into the fourth convolutional module to extract a second candidate beacon classification feature; Inputting the second candidate beacon classification feature into the fifth convolutional module to extract the target beacon classification feature; Encoding the multi-frame received signal strength indication into a target beacon range feature by inputting it into the second encoder includes: Inputting the multi-frame received signal strength indication into the second time-delay neural network to convert it into a three-dimensional first candidate beacon range feature; Inputting the first candidate beacon range feature into the sixth convolutional module to extract a second candidate beacon range feature; Inputting the second candidate beacon range feature into the seventh convolutional module to extract the target beacon range feature.

5. The method according to claim 4, wherein The decoder includes an eighth convolutional module and a multi-head attention module; the eighth convolutional module each sequentially includes a convolutional layer, a batch normalization layer, and a rectified linear unit layer; Decoding the beacon fusion feature into a target beacon enhancement feature by inputting it into the decoder includes: Inputting the beacon fusion feature into the eighth convolutional module to extract a candidate beacon enhancement feature; Inputting the candidate beacon enhancement feature into the multi-head attention module to extract the target beacon enhancement feature.

6. The method according to any one of claims 1-5, characterized in that, Detecting the real-time position of the mobile device in the indoor environment based on the target fingerprint feature includes: Load the fingerprint database configured for the indoor environment; the fingerprint database has reference fingerprint features defined at various reference positions within the indoor environment; Calculate the similarity between the target fingerprint feature and each of the reference fingerprint features; If the similarity of a certain reference fingerprint feature is the highest, mark the reference position corresponding to the reference fingerprint feature as the real-time position of the mobile device in the indoor environment.

7. A mobile device, characterized in that, The mobile device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable 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 method for Bluetooth navigation in virtual reality according to any one of claims 1-6.

8. 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, it implements the method for Bluetooth navigation in virtual reality according to any one of claims 1-6.

Images