5g-based indoor positioning method, electronic device, and storage medium

Abstract

A 5G-based indoor positioning method, through an offline stage, 5G NR signal data of an AP is collected by fingerprint, a 3D-CNN extracts local features of data in a spatial dimension, a BiLSTM processes time sequence information in a time dimension, and network parameters are obtained through neural network training.In an online stage, real-time 5G NR signal data collected is input into the neural network to obtain the position of a mobile terminal.The application also provides an electronic device and a storage medium for implementing the method, which can more accurately predict the position of the mobile terminal and improve positioning accuracy.

Description

Technical Field

[0001] This invention relates to indoor positioning methods, and more particularly to a 5G-based indoor positioning method, electronic device, and storage medium. Background Technology

[0002] In known indoor positioning technologies, fingerprint data is generated by collecting 5G New Radio (NR) data and reference point numbers and storing it in a fingerprint database. The fingerprint database is then trained using a Convolutional Neural Network (CNN) algorithm to obtain a positioning model. Finally, the positioning coordinates of the test point are obtained using a probability-weighted centroid method.

[0003] When training a fingerprint database using a CNN algorithm, only local features of the data in the spatial dimension are extracted, without taking into account the influence of the time dimension. This results in lower positioning accuracy, reduced real-time performance, and poor robustness. Summary of the Invention

[0004] In view of the above, it is necessary to provide a 5G-based indoor positioning method, electronic device, and storage medium. By using the 3D-CNN algorithm and the Bi-directional Long Short-Term Memory (BiLSTM) algorithm, the location of the mobile terminal can be predicted more accurately, thereby improving positioning accuracy.

[0005] This invention provides a 5G-based indoor positioning method applied to a first mobile terminal, comprising: in an offline phase, acquiring first 5G NR signal data corresponding to the first mobile terminal; filtering the first 5G NR signal data to generate feature values ​​for each grid in the positioning area, and generating multiple location fingerprints based on the feature values ​​of each grid to establish a location fingerprint database for the positioning area; executing a three-dimensional convolutional neural network (3D-CNN) algorithm on the multiple location fingerprints; executing a bidirectional long short-term memory (BiLSTM) algorithm and an adaptive moment estimation (Adam) algorithm on the multiple location fingerprints, and estimating the position of the first mobile terminal based on the multiple location fingerprints processed by the 3D-CNN algorithm, the BiLSTM algorithm, and the Adam algorithm.

[0006] Preferably, the 5G-based indoor positioning method of this embodiment further includes: in the online phase, when the second mobile terminal enters the positioning area, collecting second 5G NR signal data corresponding to the second mobile terminal; performing the 3D-CNN algorithm, the BiLSTM algorithm, and the Adam algorithm on the second 5G NR signal data; and matching the second 5G NR signal data processed by the 3D-CNN algorithm, the BiLSTM algorithm, and the Adam algorithm with the location fingerprint database to estimate the location of the second mobile terminal.

[0007] This invention also provides an electronic device, characterized in that the electronic device includes a memory, a processor, and a 5G-based indoor positioning program stored in the memory and executable on the processor. The electronic device further includes a data acquisition module, a data filtering module, a 3D-CNN module, a BiLSTM module, and a location estimation module. When the 5G-based indoor positioning program is executed by the processor, it performs the following steps: In an offline phase, it acquires first 5G NR signal data corresponding to the first mobile terminal; filters the first 5G NR signal data to generate feature values ​​for each grid in the positioning area, and generates multiple location fingerprints based on the feature values ​​of each grid to establish a location fingerprint database for the positioning area; executes a three-dimensional convolutional neural network (3D-CNN) algorithm on the multiple location fingerprints; executes a bidirectional long short-term memory (BiLSTM) algorithm and an Adam algorithm on the multiple location fingerprints, and estimates the location of the first mobile terminal based on the multiple location fingerprints processed by the 3D-CNN algorithm, the BiLSTM algorithm, and the Adam algorithm.

[0008] Preferably, when the 5G-based indoor positioning program is executed by the processor, it further implements the following steps: In the online phase, when the second mobile terminal enters the positioning area, it collects the second 5G NR signal data corresponding to the second mobile terminal; it executes the 3D-CNN algorithm, the BiLSTM algorithm, and the Adam algorithm on the second 5G NR signal data; and it matches the second 5G NR signal data processed by the 3D-CNN algorithm, the BiLSTM algorithm, and the Adam algorithm with the location fingerprint database to estimate the location of the second mobile terminal.

[0009] This invention also provides a storage medium storing a computer program that, when executed, implements the steps of the 5G-based indoor positioning method described above.

[0010] The 5G-based indoor positioning method, electronic device, and storage medium of this invention collect fingerprints of 5G NR signal data in an offline phase. A 3D-CNN model extracts local features of the data in the spatial dimension, while a BiLSTM model processes temporal information in the temporal dimension. Network parameters are obtained through neural network training. In the online phase, the collected real-time 5G NR signal data is input into the neural network. This method can extract spatial and temporal features from 5G NR signal data, resulting in higher positioning accuracy, higher real-time performance, and better robustness. Attached Figure Description

[0011] Figure 1 This is a schematic diagram of the network structure of 5G NR signal data in the 5G-based indoor positioning method according to an embodiment of the present invention.

[0012] Figure 2 This is a flowchart of the steps of the 5G-based indoor positioning method according to an embodiment of the present invention.

[0013] Figure 3 This is a schematic diagram of the positioning area according to an embodiment of the present invention.

[0014] Figure 4 This is a schematic diagram of the hardware architecture of the electronic device according to an embodiment of the present invention.

[0015] Figure 5 This is a functional block diagram of an electronic device according to an embodiment of the present invention.

[0016] Explanation of main component symbols Electronic devices 200 Processor 210 Memory 220 5G-based indoor positioning system 230 Data acquisition module 310 Data filtering module 320 3D-CNN Module 330 BiLSTM Module 340 Position estimation module 350 Wireless base stations AP1..AP5 Grid number L Steps S11-S15, S21-S23 The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0017] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0018] Numerous specific details are set forth in the following description to provide a thorough understanding of the invention. The described embodiments are merely some, not all, of the embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0020] It should be noted that the descriptions involving "first," "second," etc., in this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of the stated features. Furthermore, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0021] 5G New Radio (NR) technology, based on a 3D-CNN (3D-CNN) and Bidirectional Long Short-Term Memory (BiLSTM) network, utilizes an indoor positioning principle comprised of four parts: 5G NR signal data acquisition, location fingerprint database construction, neural network model training, and online real-time matching and positioning. By matching the acquired 5G NR signal data with the constructed location fingerprint database, the coordinates of the device to be positioned are estimated.

[0022] Figure 1 This is a schematic diagram of the network structure of 5G NR signal data in the 5G-based indoor positioning method of this invention. The 5G-based indoor positioning method of this invention performs indoor positioning of the mobile terminal based on the collected 5G NR signal data of the first mobile terminal, combined with a 3D-CNN model and a BiLSTM model. Figure 1As shown, the three-dimensional feature matrix of 5G NR signal data is used as the input of the 3D-CNN model. The 3D-CNN model extracts spatial features from the 5G NR signal data to obtain the spatial feature vector of the 5G NR signal data. The spatial feature vector is then input into the BiLSTM model in a temporal manner, and finally input into the fully connected layer of the Softmax function to classify the 5G NR signal data.

[0023] Figure 2 This is a flowchart illustrating the steps of a 5G-based indoor positioning method according to an embodiment of the present invention, applied to an electronic device, specifically a mobile terminal. The order of the steps in the flowchart can be changed, and some steps can be omitted, depending on different requirements.

[0024] Offline phase Step S11: Collect 5G NR signal data corresponding to the first mobile terminal during the offline phase.

[0025] In 5G NR indoor positioning, signal data such as the Synchronization Signal-Reference Signal Received Power (SS-RSRP), Synchronization Signal-Signal to Interference plus Noise Ratio (SS-SINR), Synchronization Signal-Reference Signal Received Quality (SS-RSRQ), and Synchronization Signal Acquisition Time (SS-TIME) of the 5G wireless base station (Access Point, AP) are collected.

[0026] For example, refer to Figure 3 Five wireless base stations, AP1 to AP5, are deployed in the positioning area, dividing the area into 18x10 grids, where L is the grid number. L and the coordinates satisfy formula (1): …(1).

[0027] The first mobile terminal collects 5G NR signal data from different wireless base stations (APs) at the location with grid number L.

[0028] Step S12: Filter the collected signal data to generate feature values ​​for each grid, and establish a location fingerprint database for the positioning area based on the feature values.

[0029] The collected 5G NR signal data is used The criteria include amplitude limiting to remove extreme values ​​caused by random factors. By calculating the standard deviation of the Gaussian distribution, samples conforming to the criteria are selected. set of criteria The calculation formula (2) is as follows: …Formula (2).

[0030] in, The standard deviation of the parameter, The average value of the parameters. This represents the raw data for the i-th SS-RSRP, SS-SINR, and SS-RSRQ.

[0031] refer to Figure 3 The location data formed by the feature value and the number L is stored in the location fingerprint database. The location data structure is as follows: (3) ...Formula (3); Where k is the AP number, and parameters R, Q and S correspond to the SS-RSRP value, SS-RSRQ value and SS-SINR value of the 5G NR signal, respectively.

[0032] Multiple measurements are performed at a grid point, and the valid SS-RSRP, SS-SINR, SS-RSRQ, and SS-TIME values ​​are selected as feature values. After processing the feature values, multiple location fingerprints are formed and stored in the location fingerprint database.

[0033] Step S13: Perform 3D-CNN feature processing on the multiple location fingerprints.

[0034] When using 3D-CNN for indoor localization, the fingerprint vector measured by each grid is used as input for convolution operation. The convolutional feature values ​​are processed through 3 convolutional layers and 2 sampling layers, and then output to a fully connected layer for learning and classification. Finally, the result is output.

[0035] The 3D-CNN convolution formula (4) is as follows: ...Formula (4); Where v is the position of the j-th feature cube in the i-th layer. The output is at point , where 𝑓(∗) is the activation function. The bias of this feature cube. For the first i Layer j Each feature map location The weights of the neurons above and the weights before the k-th feature map in the upper layer. k for The connection index value between the features of layer i and layer i. For the first i The size of the convolution kernel in the layer.

[0036] Step S14: Process the multiple location fingerprints using the BiLSTM algorithm and the Adaptive Moment Estimation (Adam) algorithm to obtain more accurate location fingerprints, and store them in the location fingerprint database. It should be noted that BiLSTM and Adam are both known technologies and will not be described in detail here.

[0037] Step S15: Estimate the location of the first mobile terminal based on the location fingerprint database. At this time, the location information of the grid in the positioning area has been obtained, for example, the coordinates of each grid.

[0038] Online phase Step S21: In the online phase, when the second mobile terminal enters the positioning area, 5G NR signal data corresponding to each AP of the second mobile terminal is collected. It should be noted that the offline phase and the online phase correspond to whether the second mobile terminal has entered the positioning area.

[0039] Step S22: Process the 5G NR signal data of each AP using a 3D-CNN model and a BiLSTM model.

[0040] Step S23: Match the processed 5G NR signal data with the location fingerprint database to estimate the location of the second mobile terminal.

[0041] Figure 4 This is a schematic diagram of the hardware architecture of an electronic device according to an embodiment of the present invention. The electronic device 200, for example, a mobile terminal, but not limited to, can communicate with and be connected to a processor 210, a memory 220, and a 5G-based indoor positioning system 230 via a system bus. Figure 4 Only the electronic device 200 with components 210-230 is shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0042] The memory 220 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 220 may be an internal storage unit of the electronic device 200, such as the hard disk or memory of the electronic device 200. In other embodiments, the memory may also be an external storage device of the electronic device 200, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 200. Of course, the memory 220 may also include both internal storage units and external storage devices of the electronic device 200. In this embodiment, the memory 220 is typically used to store the operating system and various application software installed on the electronic device 200, such as the program code of the 5G-based indoor positioning system 230. Furthermore, the memory 220 can also be used to temporarily store various types of data that have been output or will be output.

[0043] In some embodiments, the processor 210 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 210 is typically used to control the overall operation of the electronic device 200. In this embodiment, the processor 210 is used to run program code stored in the memory 220 or process data, for example, to run the 5G-based indoor positioning system 230.

[0044] It should be noted that, Figure 4 The electronic device 200 is merely an example. In other embodiments, the electronic device 200 may also include more or fewer components, or have different component configurations.

[0045] If the modules / units integrated in the electronic device 200 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, disks, optical discs, computer memory, read-only memory, random access memory, electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0046] Figure 5 This is a functional block diagram of an electronic device according to an embodiment of the present invention, which is used to execute a 5G-based indoor positioning method. The 5G-based indoor positioning method of this embodiment can be implemented by a computer program stored in a storage medium, such as memory 220 in the electronic device 200. When the computer program implementing the method of the present invention is loaded into memory 220 by processor 210, it drives processor 210 of the electronic device 200 to execute the 5G-based indoor positioning method of this embodiment.

[0047] The electronic device 200 of this invention includes a data acquisition module 310, a data filtering module 320, a 3D-CNN module 330, a BiLSTM module 340, and a position estimation module 350.

[0048] During the offline phase, the data acquisition module 310 acquires 5G NR signal data from the electronic device 200. The data filtering module 320 filters the acquired signal data to generate feature values ​​for each grid and establishes a location fingerprint database for the positioning area based on the feature values. The 3D-CNN module 330 performs 3D-CNN feature processing on the multiple location fingerprints; the BiLSTM module 340 performs BiLSTM and Adam algorithms on the multiple location fingerprints to obtain more accurate location fingerprints. The location estimation module 350 estimates the position of the first mobile terminal based on the location fingerprints. At this point, the location information of the grids in the positioning area, such as the coordinates of each grid, has been obtained.

[0049] During the online phase, when the electronic device 200 enters the positioning area, the data acquisition module 310 acquires 5G NR signal data from each access point (AP). The 3D-CNN module 330 and the BiLSTM module 340 process the 5G NR signal data from each AP. The location estimation module 350 matches the processed 5G NR signal data with the location fingerprint database to estimate the location of the electronic device 200.

[0050] It is understood that the module division described above is merely a logical functional division, and other division methods may be used in actual implementation. Furthermore, the functional modules in the various embodiments of this application can be integrated into the same processing unit, or each module can exist physically separately, or two or more modules can be integrated into the same unit. The integrated modules described above can be implemented in hardware or in a combination of hardware and software functional modules.

[0051] For those skilled in the art, other corresponding changes or adjustments can be made to the technical solutions and concepts provided in the embodiments of the present invention in combination with actual needs, and all such changes and adjustments should fall within the protection scope of the claims of the present invention.

Claims

1. A 5G-based indoor positioning method, applied in a first mobile terminal, characterized in that, The method includes: Collect the first 5G New Radio (NR) signal data corresponding to the first mobile terminal; The first 5G new radio signal data is filtered to generate feature values ​​for each grid in the positioning area, and multiple location fingerprints are generated based on the feature values ​​of each grid to establish a location fingerprint database for the positioning area. A 3D-CNN algorithm is applied to the fingerprints at the multiple locations. The Bidirectional Long Short-Term Memory (BiLSTM) algorithm and the Adaptive Moment Estimation (Adam) algorithm are applied to the fingerprints at the multiple locations. The location of the first mobile terminal is estimated based on the multiple location fingerprints processed by the three-dimensional convolutional neural network algorithm, the bidirectional long short-term memory algorithm, and the adaptive moment estimation algorithm.

2. The 5G-based indoor positioning method as described in claim 1, characterized in that, Also includes: When the second mobile terminal enters the positioning area, it collects the second 5G new radio signal data corresponding to the second mobile terminal; The three-dimensional convolutional neural network algorithm, the bidirectional long short-term memory algorithm, and the adaptive moment estimation algorithm are executed on the second 5G new radio signal data; and The second 5G new radio signal data, processed by the three-dimensional convolutional neural network algorithm, the bidirectional long short-term memory algorithm, and the adaptive moment estimation algorithm, is matched with the location fingerprint database to estimate the location of the second mobile terminal.

3. An electronic device, characterized in that, The electronic device includes a memory, a processor, and a 5G-based indoor positioning program stored in the memory and executable on the processor. The electronic device also includes a data acquisition module, a data filtering module, a three-dimensional convolutional neural network module, a bidirectional long short-term memory module, and a location estimation module. When the 5G-based indoor positioning program is executed by the processor, it performs the following steps: Collect the first 5G new radio signal data corresponding to the first mobile terminal; The first 5G new radio signal data is filtered to generate feature values ​​for each grid in the positioning area, and multiple location fingerprints are generated based on the feature values ​​of each grid to establish a location fingerprint database for the positioning area. A three-dimensional convolutional neural network algorithm is applied to the multiple location fingerprints. The bidirectional long short-term memory (BLS) algorithm and the adaptive moment estimation algorithm are applied to the multiple location fingerprints. The location of the first mobile terminal is estimated based on the multiple location fingerprints processed by the three-dimensional convolutional neural network algorithm, the bidirectional long short-term memory algorithm, and the adaptive moment estimation algorithm.

4. The electronic device as claimed in claim 3, characterized in that, When the 5G-based indoor positioning program is executed by the processor, it also performs the following steps: When the second mobile terminal enters the positioning area, it collects the second 5G new radio signal data corresponding to the second mobile terminal; The three-dimensional convolutional neural network algorithm, the bidirectional long short-term memory algorithm, and the adaptive moment estimation algorithm are executed on the second 5G new radio signal data; and The second 5G new radio signal data, processed by the three-dimensional convolutional neural network algorithm, the bidirectional long short-term memory algorithm, and the adaptive moment estimation algorithm, is matched with the location fingerprint database to estimate the location of the second mobile terminal.

5. A storage medium storing at least one computer instruction thereon, characterized in that, The instructions are executed by the processor and loaded into the 5G-based indoor positioning method as described in any one of claims 1-2.

Images