Tunnel positioning method, apparatus, device, medium, and product

Abstract

The application provides a tunnel positioning method, device, equipment, medium and product, the method comprises the following steps: obtaining a plurality of network parameters reported by a user terminal when the user terminal is at a to-be-positioned point in a tunnel, predicted position data of the to-be-positioned point output by an inertial navigation system, and tunnel position data; based on the plurality of network parameters and the tunnel position data, a plurality of first MR fingerprint data are matched from an MR fingerprint library; similarity analysis is performed based on the plurality of first MR fingerprint data and the predicted position data, and MR fingerprint positioning data of the to-be-positioned point is obtained; and position data correction is performed based on the MR fingerprint positioning data and the predicted position data, and actual positioning data of the to-be-positioned point is obtained. The tunnel positioning method provided by the application can accurately calculate the positioning data of a user in a tunnel environment through an algorithm without the need to separately deploy a positioning device in the tunnel environment and without the need to be limited by hardware devices, so that the flexibility is improved while the accuracy is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wireless communication, and in particular to a tunnel positioning method, device, equipment, medium and product. BACKGROUND

[0002] With the rapid development of computer technology and communication field, location-based services bring more and more convenience to real life, and global positioning system and various wireless positioning technologies have brought great convenience to users with outdoor positioning needs. However, due to the wireless shielding effect of the tunnel environment, it is difficult for people to achieve accurate positioning by means of cellular network and Beidou positioning system. Therefore, the wireless positioning system of the tunnel also has considerable demand and has very important practical significance. However, there are few software products available for the tunnel positioning system at present, and it is a very meaningful work to research the tunnel positioning technology and develop a high-precision tunnel positioning system.

[0003] The existing solutions all consider from the aspects of modifying the tunnel, modifying the equipment, and combining new technologies with hardware devices to solve the stability and accuracy problems of tunnel positioning. Since the existing solutions need to separately deploy the devices and equipment inside and outside the tunnel related to tunnel positioning, a large cost benefit is generated, and the flexibility of the tunnel positioning mode is low due to the limitation of specific hardware. SUMMARY

[0004] The present application provides a tunnel positioning method, device, equipment, medium and product to solve the problem of low flexibility of the tunnel positioning mode in the prior art.

[0005] In a first aspect, the present application provides a tunnel positioning method, comprising:

[0006] obtaining a plurality of network parameters reported by a user terminal when the user terminal is at a to-be-positioned point in a tunnel, predicted position data of the to-be-positioned point output by an inertial navigation system, and tunnel position data;

[0007] matching a plurality of first MR fingerprint data from a measurement report (MR) fingerprint library based on the plurality of network parameters and the tunnel position data;

[0008] performing similarity analysis based on the plurality of first MR fingerprint data and the predicted position data to obtain MR fingerprint positioning data of the to-be-positioned point;

[0009] performing position data correction based on the MR fingerprint positioning data and the predicted position data to obtain actual positioning data of the to-be-positioned point.

[0010] In one embodiment, the similarity analysis based on the plurality of first MR fingerprint data and the predicted position data obtains MR fingerprint positioning data of the to-be-positioned point, including:

[0011] A positioning area range is constructed with the predicted position data of the to-be-positioned point as a center and a preset error distance as a radius.

[0012] A plurality of second MR fingerprint data meeting the positioning area range is matched according to the plurality of first MR fingerprint data;

[0013] Confidence between the plurality of second MR fingerprint data and the predicted position data is iteratively calculated;

[0014] Second MR fingerprint data corresponding to confidence greater than a preset threshold is determined as third MR fingerprint data;

[0015] Grid position data in the third MR fingerprint data corresponding to target confidence is determined as MR fingerprint positioning data of the to-be-positioned point; the target confidence refers to the maximum confidence among confidences corresponding to the plurality of third MR fingerprint data.

[0016] In one embodiment, the position data correction based on the MR fingerprint positioning data and the predicted position data obtains actual positioning data of the to-be-positioned point, including:

[0017] It is judged whether the MR fingerprint positioning data has a rectification value;

[0018] If the MR fingerprint positioning data has a rectification value, actual positioning data of the to-be-positioned point is determined based on the MR fingerprint positioning data and the predicted position data, and navigation parameter error of the inertial navigation system is corrected, so that the inertial navigation system predicts position data of a next to-be-positioned point according to the corrected navigation parameter error.

[0019] In one embodiment, the actual positioning data of the to-be-positioned point is determined based on the MR fingerprint positioning data and the predicted position data, and the navigation parameter error of the inertial navigation system is corrected, including:

[0020] The predicted position data and the MR fingerprint positioning data are subtracted to obtain a deviation value;

[0021] Kalman filtering is performed based on the deviation value to obtain a filtered error value;

[0022] The predicted position data and the filtered error value are subtracted to obtain actual positioning data of the to-be-positioned point;

[0023] Based on the filtered error value, the navigation parameters output by the inertial navigation system are adjusted to correct the navigation parameter error of the inertial navigation system.

[0024] In one embodiment, the MR fingerprint database is determined as follows:

[0025] Obtain mobile signaling information;

[0026] Based on the mobile signaling information, the communication coverage area is determined;

[0027] Determine the location points of multiple base stations within the communication coverage area and the signal strength values ​​corresponding to each of the multiple base station location points;

[0028] The communication coverage area is divided into grids to obtain multiple grids;

[0029] Based on multiple base station location points and multiple signal strength values ​​within the communication coverage area, multiple base station location points and multiple signal strength values ​​within each grid are determined;

[0030] Generate a unique number for each grid cell;

[0031] Determine the raster position data for each grid cell;

[0032] Based on each grid, the unique number of each grid, and multiple base station location points and multiple signal strength values ​​within each grid, MR fingerprint data is generated, and an MR fingerprint database is constructed based on multiple MR fingerprint data.

[0033] In one embodiment, the tunnel positioning method further includes:

[0034] Acquire MR fingerprint positioning data samples when the user terminal sample is located in multiple positioning point samples in the tunnel sample;

[0035] Multiple MR fingerprint positioning data samples are clustered according to different base stations to obtain multiple types of MR fingerprint positioning data samples.

[0036] The multi-type MR fingerprint positioning data samples are trained by an autoencoder to obtain multiple noise-reduced MR fingerprint positioning data samples output by the autoencoder.

[0037] The multiple noise-reduced MR fingerprint positioning data samples are updated to the MR fingerprint database.

[0038] Secondly, the present invention also provides a tunnel positioning device, comprising:

[0039] The acquisition module is used to acquire multiple network parameters reported by the user terminal when it is at the location to be located in the tunnel, the predicted location data of the location to be located output by the inertial navigation system, and the tunnel location data.

[0040] a matching module, configured to match a plurality of first MR fingerprint data from a MR fingerprint library based on the plurality of network parameters and the tunnel location data;

[0041] a similarity analysis module, configured to perform similarity analysis based on the plurality of first MR fingerprint data and the predicted location data to obtain MR fingerprint positioning data of the to-be-positioned point;

[0042] a correction module, configured to perform location data correction based on the MR fingerprint positioning data and the predicted location data to obtain actual positioning data of the to-be-positioned point.

[0043] In a third aspect, the present application provides a device, which comprises an electronic device, the electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the tunnel positioning method according to any one of the above aspects when executing the program.

[0044] In a fourth aspect, the present application further provides a medium, which comprises a non-transitory computer-readable storage medium having a computer program stored thereon, the computer program being executable on a processor to implement the steps of the tunnel positioning method according to any one of the above aspects.

[0045] In a fifth aspect, the present application further provides a product, which comprises a computer program product, the computer program product comprising a computer program, the computer program being storable on a non-transitory computer-readable storage medium, the computer program being executable on the processor to implement the steps of the tunnel positioning method according to any one of the above aspects.

[0046] The tunnel positioning method, device, equipment, medium and product provided by the present application greatly reduce the subsequent calculation amount, improve the calculation speed, and further obtain the actual positioning data of the to-be-positioned point through similarity analysis and correction based on the plurality of first MR fingerprint data and the predicted location data, so that the positioning data of the user in the tunnel environment can be accurately calculated through the algorithm without the need for separately deploying positioning equipment in the tunnel environment and without the need for being limited by the hardware equipment, thereby improving the flexibility of the tunnel positioning method while ensuring the accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to make the technical solutions in the present application or prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0048] Figure 1 is one of the flow diagrams of the tunnel positioning method provided by the present application.

[0049] Figure 2 is the second flow diagram of the tunnel positioning method provided by the present application.

[0050] Figure 3 is the flow diagram of the navigation parameter error correction provided by the present application.

[0051] Figure 4 is the structural diagram of the auto-encoder provided by the present application.

[0052] Figure 5 is the structural diagram of the tunnel positioning device provided by the present application.

[0053] Figure 6 is the structural diagram of the electronic device provided by the present application. DETAILED DESCRIPTION

[0054] In order to make the technical solutions in the present application or prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0055] The terms "first", "second", and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein.

[0056] The following will be described in conjunction with Figures 1-6 The tunnel positioning method, device, equipment, medium and product provided by the present application are described.

[0057] It should be noted that the tunnel positioning method provided by the embodiment of the present application is realized based on a tunnel positioning device. The tunnel positioning method provided by the embodiment of the present application can be used to calculate accurate positioning data when there is no positioning information in a tunnel environment. Similarly, the tunnel positioning method can also be applied to other application scenarios, which will not be described here. The tunnel positioning method is described by taking the tunnel positioning device as an execution subject.

[0058] In combination Figure 1 And Figure 2 , Figure 1 is one of the flowcharts of the tunnel positioning method provided by the present application, Figure 2 is another flowchart of the tunnel positioning method provided by the present application.

[0059] As Figure 1 indicated, the method comprises the following steps:

[0060] Step 101, acquiring a plurality of network parameters reported by a user terminal when the user terminal is at a to-be-positioned point in a tunnel, predicted position data of the to-be-positioned point output by an inertial navigation system, and tunnel position data;

[0061] Step 102, matching a plurality of first MR fingerprint data from a measurement report (MR) fingerprint library based on the plurality of network parameters and the tunnel position data;

[0062] Step 103, performing similarity analysis based on the plurality of first MR fingerprint data and the predicted position data to obtain MR fingerprint positioning data of the to-be-positioned point;

[0063] Step 104, performing position data correction based on the MR fingerprint positioning data and the predicted position data to obtain actual positioning data of the to-be-positioned point.

[0064] Specifically, when a user enters a tunnel, the user terminal will initiate a positioning request to the tunnel positioning device.

[0065] Further, after the tunnel positioning device receives the positioning request sent by the user terminal, the tunnel positioning device acquires a plurality of network parameters reported by the user terminal when the user terminal is at a to-be-positioned point in the tunnel, including but not limited to real-time information such as a user terminal model, a received signal strength indication (RSSI), a received signal strength quality (RSSQ), a received signal strength power (RSSP), a carrier number, and a base station number.

[0066] Meanwhile, the tunnel positioning apparatus also acquires tunnel location data of the tunnel in which the user is located.

[0067] In addition, the tunnel positioning apparatus also acquires predicted location data of the to-be-positioned point output by the inertial navigation system.

[0068] It should be noted that the inertial navigation system is a navigation technology that uses inertial sensors such as accelerometers and gyroscopes to measure and calculate the position, speed, and direction of a vehicle, and does not rely on external reference objects, but calculates the changes in position and direction by measuring the acceleration and angular velocity of the vehicle. The inertial navigation system outputs navigation parameters through an inertial navigation algorithm, and the algorithm flow is as follows: according to the global positioning system (GPS) before entering the tunnel, the acceleration vector is projected in the direction of the tunnel to calculate the actual acceleration, and the initial position, direction, speed, and acceleration of the vehicle are determined according to the tunnel direction, azimuth, and historical GPS.

[0069] Further, the tunnel positioning apparatus calls a measurement report (MR) fingerprint library, wherein the MR fingerprint library includes a plurality of MR fingerprint data, and the MR fingerprint data is a kind of geographical position specific identifier formed by collecting and analyzing signal parameters of a user terminal at different positions in a communication network, so each MR fingerprint data identifies a specific geographical position and can be applied to positioning services.

[0070] Further, the tunnel positioning apparatus matches the first MR fingerprint data associated with the current to-be-positioned point and having strong signal strength from the MR fingerprint library based on information such as user terminal model, RSSI, RSSQ, RSSP, carrier number, base station number, and tunnel location data, through a cosine similarity calculation method.

[0071] Therefore, the plurality of first MR fingerprint data matched can cover the entire area of the tunnel in which the user is currently located, and only the first MR fingerprint data of the associated area is selected, which can greatly reduce the amount of calculation when performing similarity calculation with the predicted data output by the inertial navigation system in the subsequent process, thereby improving the speed of tunnel positioning.

[0072] The cosine similarity formula is as follows:

[0073]

[0074] Further, the tunnel positioning apparatus performs confidence calculation based on the plurality of first MR fingerprint data and the predicted location data to obtain the confidence between each first MR fingerprint data and the predicted location data.

[0075] Further, the tunnel positioning device performs similarity analysis according to the confidence between each first MR fingerprint data and the predicted position data, and obtains MR fingerprint positioning data of the to-be-positioned point that is most similar to the predicted position data.

[0076] Further, the tunnel positioning device determines actual positioning data of the to-be-positioned point based on the MR fingerprint positioning data and the predicted position data, and corrects the navigation parameter error of the inertial navigation system, so that the inertial navigation system can predict the position data of the next to-be-positioned point according to the corrected navigation parameter error.

[0077] It should be noted that the user will move over time when in the tunnel, but the user terminal will send a positioning request every short time interval, and each positioning request corresponds to a to-be-positioned point. For each to-be-positioned point, the above-described algorithm is used for calculation. The positioning data calculation method of one to-be-positioned point is described in the embodiment of the application.

[0078] Further, through the above algorithm, the tunnel positioning device can obtain and accumulate MR fingerprint positioning data samples of the user terminal sample in the tunnel sample at multiple to-be-positioned point samples. It should be noted that the samples described herein all represent multiple samples.

[0079] Further, the tunnel positioning device performs data noise reduction on the accumulated sample data in batches to obtain a noise reduction result, and updates the noise reduction result to the MR fingerprint library.

[0080] The tunnel positioning method provided by the application greatly reduces the subsequent calculation amount, improves the calculation speed, and further obtains the actual positioning data of the to-be-positioned point through similarity analysis and correction based on the multiple first MR fingerprint data and the predicted position data. Therefore, it is not necessary to separately deploy a positioning device in a tunnel environment, nor is it necessary to be limited by hardware devices. The positioning data of the user in the tunnel environment can be accurately calculated through the algorithm, thereby improving the flexibility of the tunnel positioning method while ensuring the accuracy.

[0081] Further, the MR fingerprint library is determined by the following method:

[0082] Obtain mobile signaling information;

[0083] Determine a communication coverage area based on the mobile signaling information;

[0084] Determine multiple base station position points in the communication coverage area and signal strength values corresponding to the multiple base station position points, respectively;

[0085] grid the communication coverage area to obtain a plurality of grids;

[0086] determine a plurality of base station location points and a plurality of signal strength values in each grid based on the plurality of base station location points and the plurality of signal strength values in the communication coverage area;

[0087] generate a unique number for each grid;

[0088] determine grid location data for each grid;

[0089] generate MR fingerprint data based on each grid, the unique number for each grid, and the plurality of base station location points and the plurality of signal strength values in each grid, and construct an MR fingerprint library according to the plurality of MR fingerprint data.

[0090] Specifically, the tunnel positioning device acquires mobile signaling information, wherein the mobile signaling information is control information used for establishing, maintaining, and ending a communication connection in a mobile communication network.

[0091] Further, the tunnel positioning device analyzes the mobile signaling information, and signaling exchange between a base station and a user equipment can provide information about signal strength, reception quality, and equipment location, which can be used to evaluate and determine a communication coverage area.

[0092] Further, the tunnel positioning device determines a plurality of base station location points in the communication coverage area and signal strength values corresponding to the plurality of base station location points, respectively.

[0093] Further, the tunnel positioning device can determine a minimum circumscribed rectangle of the communication coverage area through GPS, use a lower left corner coordinate of the minimum circumscribed rectangle as an origin, and calculate a coordinate offset corresponding to an actual distance.

[0094] Further, the tunnel positioning device can grid the communication coverage area according to a predetermined row-column rule through GPS to obtain a plurality of grids, and generate a unique number for each grid to finally form a grid map.

[0095] Further, the tunnel positioning device determines a plurality of base station location points and a plurality of signal strength values in each grid based on the plurality of base station location points and the plurality of signal strength values in the communication coverage area.

[0096] Further, the tunnel positioning device determines grid location data for each grid. It should be noted that since a grid is a range, historical user positioning data or MR fingerprint positioning data can exist in the grid, and thus the grid location data for the grid is a mean value of all historical positioning data or MR fingerprint positioning data in the range.

[0097] Further, the tunnel positioning device generates MR fingerprint data based on each grid, a unique number of each grid, and a plurality of base station position points and a plurality of signal strength values within each grid.

[0098] Further, the tunnel positioning device constructs an MR fingerprint library according to the plurality of MR fingerprint data.

[0099] The embodiment of the present application collects mobile signaling information, determines the communication coverage area and the base station position points and signal strength values within the range thereof, further divides the communication coverage area into a plurality of grids, determines the base station position points and signal strength values within the range of each grid, generates a unique number and grid position data for each grid, generates MR fingerprint data through the grid and a plurality of data within the grid, and finally constructs an MR fingerprint library, so that subsequent positioning algorithm analysis can be based on the MR fingerprint library, thereby improving the flexibility of tunnel positioning while ensuring the accuracy of tunnel positioning.

[0100] Further, based on step 103, the similarity analysis based on the plurality of first MR fingerprint data and the predicted position data of the to-be-positioned point obtains MR fingerprint positioning data of the to-be-positioned point, which comprises:

[0101] A positioning area range is constructed with the predicted position data of the to-be-positioned point as the center and a preset error distance as the radius;

[0102] A plurality of second MR fingerprint data that meet the positioning area range are matched according to the plurality of first MR fingerprint data;

[0103] Confidence degrees between the plurality of second MR fingerprint data and the predicted position data are iteratively calculated;

[0104] Second MR fingerprint data corresponding to a confidence degree greater than a preset threshold are determined as third MR fingerprint data;

[0105] Grid position data in the third MR fingerprint data corresponding to a target confidence degree are determined as MR fingerprint positioning data of the to-be-positioned point; the target confidence degree refers to the maximum confidence degree among the confidence degrees corresponding to the plurality of third MR fingerprint data.

[0106] Specifically, the tunnel positioning device constructs a positioning area range with the predicted position data of the to-be-positioned point output by the inertial navigation system as the center and a preset error distance as the radius, wherein the preset error distance is set according to actual conditions.

[0107] Further, the tunnel positioning device respectively calculates distances between the plurality of first MR fingerprint data and the center.

[0108] Further, the tunnel positioning device determines the first MR fingerprint data corresponding to the distance less than the radius as the second MR fingerprint data.

[0109] Therefore, the tunnel positioning device can match the multiple second MR fingerprint data satisfying the positioning area range according to the multiple first MR fingerprint data.

[0110] Further, the tunnel positioning device calculates the confidence between the multiple second MR fingerprint data and the predicted position data. It should be noted that the formula for calculating the confidence is the same as the formula for calculating the cosine similarity.

[0111] Further, the tunnel positioning device compares the multiple confidence with the preset threshold value to obtain a comparison result.

[0112] Further, the tunnel positioning device determines the second MR fingerprint data corresponding to the confidence greater than the preset threshold value as the third MR fingerprint data according to the comparison result.

[0113] It should be noted that the preset threshold value is set according to the actual situation, and can be set to a 4 decimal value in the range of 0-1. The smaller the value, the smaller the set threshold value. Therefore, the greater the confidence, the closer the trajectory data set by the inertial navigation to the predicted position data, that is, the MR fingerprint data, and the more consistent the data. Finally, the data with the smallest gap is selected as the matching data.

[0114] Further, the tunnel positioning device determines the maximum confidence in the multiple confidence corresponding to the multiple third MR fingerprint data as the target confidence.

[0115] Further, the tunnel positioning device determines the grid position data in the third MR fingerprint data corresponding to the target confidence as the MR fingerprint positioning data of the to-be-positioned point.

[0116] The embodiment of the application greatly reduces the subsequent calculation amount, improves the calculation speed, and thus improves the tunnel positioning speed, based on the multiple network parameters and tunnel position data reported by the user terminal when the user terminal is at the to-be-positioned point in the tunnel, matches the multiple first MR fingerprint data associated with the current position of the user and having better signal strength from the MR fingerprint library.

[0117] Further, based on step 104, the position data correction based on the MR fingerprint positioning data and the predicted position data obtains the actual positioning data of the to-be-positioned point, which comprises:

[0118] determining whether the MR fingerprint positioning data has a rectification value;

[0119] If the MR fingerprint positioning data has the value of rectification, actual positioning data of the to-be-positioned point is determined based on the MR fingerprint positioning data and the predicted position data, and navigation parameter error of the inertial navigation system is corrected so that the inertial navigation system predicts position data of a next to-be-positioned point according to the corrected navigation parameter error.

[0120] Specifically, the tunnel positioning device determines whether the MR fingerprint positioning data has the value of rectification according to the size of the confidence degree corresponding to the MR fingerprint positioning data.

[0121] It should be noted that if the confidence degree is high, the MR fingerprint positioning data has the value of rectification, and the data can be rectified to return more accurate positioning data. However, if the confidence degree is low, the MR fingerprint positioning data does not have the value of rectification, and the data is not reliable enough, and the data is not rectified to avoid introducing more errors. Such a processing manner ensures that rectification is only performed when the data has a certain degree of reliability, thereby ensuring the accuracy and reliability of the final positioning result.

[0122] Therefore, further, if the MR fingerprint positioning data does not have the value of rectification, the tunnel positioning device does not rectify the MR fingerprint positioning data.

[0123] Further, if the MR fingerprint positioning data has the value of rectification, the tunnel positioning device determines actual positioning data of the to-be-positioned point based on the MR fingerprint positioning data and the predicted position data, and corrects navigation parameter error of the inertial navigation system so that the inertial navigation system predicts position data of a next to-be-positioned point according to the corrected navigation parameter error.

[0124] In the case that the MR fingerprint positioning data has the value of rectification, the embodiment of the application determines actual positioning data of the to-be-positioned point based on the MR fingerprint positioning data and the predicted position data, and corrects navigation parameter error of the inertial navigation system, so that the inertial navigation system can more accurately predict position of a next to-be-positioned point, thereby continuously improving prediction accuracy of the inertial navigation system. Therefore, positioning data determined by combining predicted positioning data of the inertial navigation system and the MR fingerprint positioning data is more accurate.

[0125] Further, the determination of the actual positioning data of the to-be-positioned point based on the MR fingerprint positioning data and the predicted position data and the correction of the navigation parameter error of the inertial navigation system include:

[0126] Subtracting the predicted position data from the MR fingerprint positioning data to obtain a deviation value;

[0127] Performing Kalman filtering based on the deviation value to obtain a filtered error value;

[0128] subtracting the predicted position data and the MR fingerprint positioning data of the to-be-positioned point, to obtain a deviation value of the to-be-positioned point;

[0129] feedback adjusting, based on the filtered error value, a navigation parameter output by the inertial navigation system, to correct a navigation parameter error of the inertial navigation system.

[0130] combining Figure 3 , Figure 3 is a flowchart of the method for correcting the navigation parameter error. According to the MR fingerprint positioning data and the predicted position data, an observation vector is constructed, a state vector is constructed, a state equation of the observation vector and the state vector is further established, a navigation parameter error of the inertial navigation system is output, and the predicted position data predicted by the inertial navigation system is corrected.

[0131] Specifically, the tunnel positioning device subtracts the predicted position data and the MR fingerprint positioning data to obtain a deviation value.

[0132] Further, the tunnel positioning device performs Kalman filtering on the deviation value to obtain a filtered error value.

[0133] Further, the tunnel positioning device subtracts the predicted position data and the filtered error value to obtain actual positioning data of the to-be-positioned point.

[0134] Further, the tunnel positioning device feedback adjusts, based on the filtered error value, a navigation parameter output by the inertial navigation system, to correct a navigation parameter error of the inertial navigation system.

[0135] In an embodiment, the MR and the inertial navigation are cooperated in a manner that a deviation of the MR and the inertial navigation is taken as an optimization estimation target to perform Kalman filtering, and a subtraction calculation formula of the predicted position data and the MR fingerprint positioning data is as follows:

[0136]

[0137]

[0138]

[0139] wherein, representing predicted position data of a to-be-positioned point output by an inertial navigation system; representing MR fingerprint positioning data of the to-be-positioned point determined based on an MR fingerprint library; r represents actual positioning data of the to-be-positioned point; representing an error value between the predicted position data and the actual positioning data; representing an error value between the MR fingerprint positioning data and the actual positioning data; z represents a deviation value between the predicted position data and the MR fingerprint positioning data.

[0140] The system state equation and the observation equation of Kalman filtering are as follows:

[0141]

[0142]

[0143] wherein, represents a system noise, which is a zero offset error of the user terminal accelerometer; represents an error value in a current state ; represents an error value in a next state ; represents a differential equation of the error value ; represents an observation noise; represents an observation matrix.

[0144] Since is relatively random, the filtered error calculated by the system state equation and the observation equation of Kalman filtering is approximately equal to , further, the is corrected back to the predicted position data, and the following is obtained: , that is, the actual positioning data of the to-be-positioned point can be obtained.

[0145] The embodiment of the application calculates the deviation value between the predicted position data and the MR fingerprint positioning data, filters the error value by Kalman filtering, corrects the error value back to the inertial navigation prediction result, and thus more accurate actual positioning data can be obtained. At the same time, the navigation parameters are feedback adjusted based on the error value, so that the inertial navigation system corrects the navigation parameter error, the position of the next to-be-positioned point can be more accurately predicted, the prediction accuracy of the inertial navigation system is continuously improved, and the positioning data determined by combining the predicted positioning data of the inertial navigation system and the MR fingerprint positioning data will be more accurate.

[0146] Further, the tunnel positioning method further comprises:

[0147] obtaining MR fingerprint positioning data samples of the user terminal sample at a plurality of to-be-positioned point samples in the tunnel sample;

[0148] clustering a plurality of MR fingerprint positioning data samples according to different base stations to obtain a plurality of types of MR fingerprint positioning data samples;

[0149] training the plurality of types of MR fingerprint positioning data samples through a self-encoder to obtain a plurality of denoised MR fingerprint positioning data samples output by the self-encoder;

[0150] update the plurality of denoised MR fingerprint positioning data samples to the MR fingerprint library.

[0151] Specifically, the tunnel positioning device acquires MR fingerprint positioning data samples when user terminal samples are in a plurality of to-be-positioned point samples in a tunnel sample.

[0152] Further, the tunnel positioning device clusters the plurality of MR fingerprint positioning data samples according to different base stations to obtain a plurality of MR fingerprint positioning data samples of different types.

[0153] Further, the tunnel positioning device trains the plurality of MR fingerprint positioning data samples of different types through a self-encoder to obtain a plurality of denoised MR fingerprint positioning data samples output by the self-encoder.

[0154] In an embodiment, the MR fingerprint positioning data samples are subjected to anomaly detection, and data exceeding a k times standard deviation threshold of the same type (i.e., under the same base station) is removed, and the formula is: |x|<=μ±kσ, wherein x represents the MR fingerprint positioning data sample, μ represents the mean, and kσ represents the k times standard deviation.

[0155] After the anomaly is proposed, the noise data is filtered through the self-encoder, and therefore, the input and output of the self-encoder are all MR fingerprint positioning data samples. Triplets Loss is calculated for the middle layer during training and added to the total loss, and triplets are established for different base stations under the same grid to improve cohesion and reduce coupling. Figure 4 , Figure 4 FIG. 1 is a structural schematic diagram of a self-encoder provided by the present application.

[0156] During training, Triplets Loss is calculated for the middle layer and added to the total loss, and triplets can be established for different base stations under the same grid in the following manner:

[0157] The three-axis acceleration and three-axis rotation angle of the user terminal are collected, and an Euler conversion matrix is calculated to map the acceleration from the user terminal coordinate system to the earth coordinate system;

[0158] The Euler conversion matrix is:

[0159]

[0160] The three are multiplied to obtain the final Euler conversion matrix:

[0161]

[0162] wherein, represents a yaw angle; represents a pitch angle; represents a roll angle.

[0163] Further, the tunnel positioning device updates the plurality of noise-reduced MR fingerprint positioning data samples to the MR fingerprint library and to the corresponding grid, and the subsequent user in the grid position can directly use the stored positioning data.

[0164] Further, the tunnel positioning device continuously maintains the MR fingerprint library and periodically re-fits the weights of the auto-encoder.

[0165] According to the MR fingerprint positioning data samples of the user terminal at a plurality of to-be-positioned points in the tunnel, the embodiment of the application obtains a plurality of types of MR fingerprint positioning data samples by clustering according to different base stations, further processes these data samples by the auto-encoder to generate a plurality of noise-reduced MR fingerprint positioning data samples, and the noise-reduced data samples are then updated to the MR fingerprint library to provide useful data for subsequent user positioning, thereby improving the positioning accuracy and flexibility in a complex environment and providing more reliable positioning services for users.

[0166] The entire process is described in detail below according to an embodiment:

[0167] The user terminal initiates a positioning request in the tunnel, and the request is received by the signal strength collection module. Then, the module collects base station mobile signaling data by calling an interface, further encapsulates related parameters, and calls a fingerprint positioning service interface. After the fingerprint positioning module receives the interface call request, the following algorithm analysis process is unfolded.

[0168] First step: by using the base station unique code (Identity document, ID) and the base station type as query parameters, the corresponding list can be accurately positioned and obtained from the huge MR fingerprint library table, which can be considered as MR fingerprint data. This query process is based on accurate base station information, which ensures that the required MR fingerprint library table list can be quickly and accurately obtained, thereby providing reliable data support for subsequent operations. As follows:

[0169] Database name: tunnel, database category: Postgresql, table name: tunnel_library_rela

[0170] select case

[0171] when t.type = 1 then

[0172] 'tunnel_library_4g_' || t.tunnel_id

[0173] else

[0174] 'tunnel_library_5g_' || t.tunnel_id

[0175] end as fingerprint_table_name

[0176] from tunnel_library_rela t

[0177] where t.site_id = base station ID

[0178] and t.type = base station type.

[0179] Step 2: If using base station ID and base station type as query conditions fails to retrieve the corresponding MR fingerprint database sub-table list, then base station positioning is used to roughly determine the current location. This positioning method is based on the coverage area and related signal strength of the base station. Although it cannot provide precise location information, it can provide an approximate positioning solution when the MR fingerprint database sub-table list cannot be obtained.

[0180] Step 3: If the corresponding MR fingerprint database sub-table is successfully retrieved using the base station ID and base station type, the fingerprint positioning method is used to determine the precise location. Fingerprint positioning technology matches the previously established fingerprint database with the currently collected signal fingerprints, enabling more accurate and refined positioning. This positioning method is more precise than base station positioning, providing more reliable location information and meeting higher precision positioning requirements. Therefore, after successfully retrieving the corresponding MR fingerprint database sub-table, the fingerprint positioning method is prioritized to ensure the accuracy and reliability of the positioning results.

[0181] (1) After obtaining the list of MR fingerprint database sub-tables, we will iterate through them. For each sub-table item, we will query the fingerprint database data in the corresponding sub-table using the table name and base station ID. Subsequently, we will summarize and integrate all the fingerprint database data obtained from each sub-table. This summarization process will ensure that we obtain a comprehensive and complete dataset for subsequent analysis and processing.

[0182] Database name: tunnel, Database type: PostgreSQL, Table name: Query partitioned tables of multiple fingerprint databases, and summarize the data of all partitioned tables, traversing the MR fingerprint database partitioned tables in the data.

[0183] select

[0184] t.grid_id,

[0185] t.scrsrp

[0186] t.scrsrq

[0187] from

[0188] MR fingerprint library table table name t

[0189] where

[0190] t.site_id = base station ID.

[0191] (2) In order to obtain accurate current location fingerprint data, first, the collected base station mobile signaling fingerprint data is parsed and cleaned to ensure the availability and accuracy of the data. Further, the previously summarized MR fingerprint library table dataset is traversed, and for each table data, the cosine similarity calculation formula is used to calculate the confidence of the cleaned current location fingerprint data and the MR fingerprint library table data. Through this calculation process, the similarity between the current location fingerprint data and the MR fingerprint library table data can be determined. Further, the MR fingerprint library table data with the highest confidence is selected, and its corresponding geographic grid ID is obtained.

[0192] (3) If the calculated confidence is lower than the preset minimum threshold, we will use the base station positioning result as the final positioning basis. This is because in the case of insufficient confidence, the relevance between the MR fingerprint library table data and the current location fingerprint data is weak, and it is difficult to ensure the accuracy of positioning. Therefore, in order to ensure the reliability of the positioning result, the base station positioning method is relied on, which estimates the position based on the base station signal strength, and in the case of confidence below the threshold, it can be used as an effective supplementary positioning means. Such a strategy ensures that relatively accurate location information can be obtained in various situations.

[0193] (4) If the calculated confidence exceeds the set minimum threshold, the corresponding latitude and longitude information will be further calculated through the grid ID. This step involves accurate query and conversion of geographic grid data to ensure that accurate location coordinates can be obtained.

[0194] (5) The latitude and longitude information obtained after calculation will be further processed for tunnel location fitting. In the fitting process, it will be carefully checked whether there is tunnel data within a specific range. If there is no tunnel data available for fitting within the specified range, the original latitude and longitude information is returned to ensure data integrity. However, once the tunnel location is successfully fitted, the fitted and matched latitude and longitude information is returned. The corrected latitude and longitude is obtained after considering the influencing factors of tunnel location, so it is more accurate and reliable. The introduction of this step aims to improve the positioning accuracy of latitude and longitude through tunnel location fitting, and to provide users with more accurate location information.

[0195] Fourth step: When the confidence exceeds the preset threshold, it indicates that there is a high correlation between the current location fingerprint data and the MR fingerprint library table data, and it has a certain credibility. Therefore, these data are transmitted to the inertial navigation positioning module for correction processing. Through a series of algorithm calculations of the inertial navigation positioning module, the accuracy of positioning can be further improved, and errors can be reduced. Finally, the data after correction processing will return more accurate positioning latitude and longitude information. However, if the confidence is low, because the data is not reliable enough, it will not be transmitted for correction to avoid introducing more errors. Such a processing method ensures that only when the data has a certain credibility, the correction operation will be performed, thereby ensuring the accuracy and reliability of the final positioning result.

[0196] The effect evaluation after tunnel positioning is as follows:

[0197] 1. After the tunnel positioning is turned on, when there is no corresponding location fingerprint information, the positioning can ensure 100% in the tunnel, and the 3-minute positioning error is within 120 meters (the error increases with time, and the upper limit of the error is estimated to be 350 meters for 3 minutes, and the specific effect is subject to the actual road test) ;

[0198] 2. After the tunnel positioning is turned on, when there is corresponding location fingerprint information and the confidence is less than the preset threshold, the positioning can ensure 100% in the tunnel, and the 3-minute positioning error is within 100 meters (the error increases with time, and the upper limit of the error is estimated to be 350 meters for 3 minutes, and the specific effect is subject to the actual road test) ;

[0199] 3. After the tunnel positioning is turned on, when there is corresponding location fingerprint information and the confidence is greater than the preset threshold, the positioning can ensure 100% in the tunnel, and the 3-minute positioning error is within 60 meters;

[0200] 4. After the tunnel positioning is turned on, if the signal in the tunnel is missing, the positioning can ensure 100% in the tunnel, and the 3-minute positioning error is within 110 meters.

[0201] The tunnel positioning device provided by the present application is described below. The tunnel positioning device described below can be referred to in conjunction with the tunnel positioning method described above.

[0202] Reference Figure 5 , Figure 5 is a structural schematic diagram of the tunnel positioning device provided by the present application.

[0203] The tunnel positioning device comprises:

[0204] The acquisition module 510 is configured to acquire a plurality of network parameters reported by a user terminal when the user terminal is at a to-be-positioned point in a tunnel, predicted position data of the to-be-positioned point output by an inertial navigation system, and tunnel position data.

[0205] The matching module 520 is configured to match a plurality of first MR fingerprint data from the MR fingerprint library based on the plurality of network parameters and the tunnel location data.

[0206] The similarity analysis module 530 is configured to perform similarity analysis based on the plurality of first MR fingerprint data and the predicted location data to obtain MR fingerprint positioning data of the to-be-positioned point.

[0207] The correction module 540 is configured to perform location data correction based on the MR fingerprint positioning data and the predicted location data to obtain actual positioning data of the to-be-positioned point.

[0208] The tunnel positioning device provided by the application greatly reduces the subsequent calculation amount, improves the calculation speed, and further obtains the actual positioning data of the to-be-positioned point through similarity analysis and correction based on the plurality of first MR fingerprint data and the predicted location data. Therefore, the positioning device does not need to be separately deployed in the tunnel environment and is not limited by the hardware device, so that the positioning data of the user in the tunnel environment can be accurately calculated through the algorithm, thereby improving the flexibility of the tunnel positioning method while ensuring the accuracy.

[0209] Further, the tunnel positioning device is further configured to:

[0210] obtain mobile signaling information;

[0211] determine a communication coverage area based on the mobile signaling information;

[0212] determine a plurality of base station location points in the communication coverage area and a plurality of signal strength values corresponding to the plurality of base station location points, respectively;

[0213] divide the communication coverage area into a plurality of grids;

[0214] determine a plurality of base station location points and a plurality of signal strength values in each grid based on the plurality of base station location points and the plurality of signal strength values in the communication coverage area;

[0215] generate a unique number for each grid;

[0216] determine grid location data of each grid;

[0217] generate MR fingerprint data based on each grid, the unique number of each grid, and the plurality of base station location points and the plurality of signal strength values in each grid, and construct an MR fingerprint library according to the plurality of MR fingerprint data.

[0218] Further, the similarity analysis module 530 is further configured to:

[0219] construct a positioning area range with the predicted position data of the to-be-positioned point as a center and a preset error distance as a radius;

[0220] match a plurality of second MR fingerprint data satisfying the positioning area range according to the plurality of first MR fingerprint data;

[0221] calculate confidence degrees between the plurality of second MR fingerprint data and the predicted position data;

[0222] determine the second MR fingerprint data corresponding to a confidence degree greater than a preset threshold as third MR fingerprint data;

[0223] determine grid position data in the third MR fingerprint data corresponding to a target confidence degree as MR fingerprint positioning data of the to-be-positioned point; the target confidence degree refers to a maximum confidence degree among confidence degrees corresponding to the plurality of third MR fingerprint data respectively.

[0224] Further, the correction module 540 is further configured to:

[0225] determine whether the MR fingerprint positioning data has a value for rectification;

[0226] if the MR fingerprint positioning data has the value for rectification, determine actual positioning data of the to-be-positioned point based on the MR fingerprint positioning data and the predicted position data, and correct a navigation parameter error of the inertial navigation system, so that the inertial navigation system predicts position data of a next to-be-positioned point according to the corrected navigation parameter error.

[0227] Further, the correction module 540 is further configured to:

[0228] subtract the predicted position data and the MR fingerprint positioning data to obtain a deviation value;

[0229] perform Kalman filtering based on the deviation value to obtain a filtered error value;

[0230] subtract the predicted position data and the filtered error value to obtain actual positioning data of the to-be-positioned point;

[0231] perform feedback adjustment on a navigation parameter output by the inertial navigation system based on the filtered error value, to correct a navigation parameter error of the inertial navigation system.

[0232] Further, the tunnel positioning apparatus is further configured to:

[0233] Obtaining MR fingerprint positioning data samples of user terminal samples in a plurality of to-be-positioned point samples in a tunnel sample;

[0234] Clustering a plurality of MR fingerprint positioning data samples according to different base stations to obtain a plurality of MR fingerprint positioning data samples of different types;

[0235] Training the plurality of MR fingerprint positioning data samples of different types through a self-encoder to obtain a plurality of denoised MR fingerprint positioning data samples output by the self-encoder;

[0236] Updating the plurality of denoised MR fingerprint positioning data samples to the MR fingerprint library.

[0237] Figure 6 is the structural schematic diagram of the electronic equipment provided by the application, as Figure 6 shown, the electronic equipment can include: processor (processor) 610, communications interface (communications interface) 620, memory (memory) 630 and communication bus 640, wherein, processor 610, communications interface 620, memory 630 complete mutual communication through communication bus 640.Processor 610 can call the logic instruction in memory 630 to execute the tunnel positioning method, the method includes: obtaining a plurality of network parameters reported by a user terminal in a to-be-positioned point in a tunnel, predicted position data of the to-be-positioned point output by an inertial navigation system and tunnel position data;Based on the plurality of network parameters and the tunnel position data, a plurality of first MR fingerprint data are matched from the measurement report MR fingerprint library;Based on the plurality of first MR fingerprint data and the predicted position data, similarity analysis is carried out to obtain MR fingerprint positioning data of the to-be-positioned point;Based on the MR fingerprint positioning data and the predicted position data, position data correction is carried out to obtain actual positioning data of the to-be-positioned point.

[0238] Further, the logic instructions in the memory 630 described above can be implemented in the form of software functional units and sold or used as independent products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0239] In another aspect, the present application also provides a computer program product, which comprises a computer program stored on a non-transitory computer readable storage medium, and the computer program comprises program instructions, when the program instructions are executed by a computer, the computer can execute the tunnel positioning method provided by the above-mentioned embodiments, and the method comprises the following steps: acquiring a plurality of network parameters reported by a user terminal at a to-be-positioned point in a tunnel, predicted position data of the to-be-positioned point output by an inertial navigation system, and tunnel position data; matching a plurality of first MR fingerprint data from a measurement report (MR) fingerprint library based on the plurality of network parameters and the tunnel position data; performing similarity analysis based on the plurality of first MR fingerprint data and the predicted position data to obtain MR fingerprint positioning data of the to-be-positioned point; and performing position data correction based on the MR fingerprint positioning data and the predicted position data to obtain actual positioning data of the to-be-positioned point.

[0240] In another aspect, the present application also provides a computer program product, which comprises a computer program stored on a non-transitory computer readable storage medium, and the computer program comprises program instructions, when the program instructions are executed by a computer, the computer can execute the tunnel positioning method provided by the above-mentioned embodiments, and the method comprises the following steps: acquiring a plurality of network parameters reported by a user terminal at a to-be-positioned point in a tunnel, predicted position data of the to-be-positioned point output by an inertial navigation system, and tunnel position data; matching a plurality of first MR fingerprint data from a measurement report (MR) fingerprint library based on the plurality of network parameters and the tunnel position data; performing similarity analysis based on the plurality of first MR fingerprint data and the predicted position data to obtain MR fingerprint positioning data of the to-be-positioned point; and performing position data correction based on the MR fingerprint positioning data and the predicted position data to obtain actual positioning data of the to-be-positioned point.

[0241] The apparatus embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units. Part or all of the modules can be selected according to actual needs to achieve the purposes of the embodiments. Those skilled in the art can understand and implement without creative labor.

[0242] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and necessary universal hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, and the computer software products can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0243] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of tunnel positioning, characterized by, The method comprises the following steps: acquiring a plurality of network parameters reported by a user terminal at a to-be-positioned point in a tunnel, predicted position data of the to-be-positioned point output by an inertial navigation system, and tunnel position data; matching a plurality of first MR fingerprint data from a measurement report (MR) fingerprint library based on the plurality of network parameters and the tunnel position data; performing similarity analysis based on the plurality of first MR fingerprint data and the predicted position data to obtain MR fingerprint positioning data of the to-be-positioned point; performing position data correction based on the MR fingerprint positioning data and the predicted position data to obtain actual positioning data of the to-be-positioned point; the similarity analysis based on the plurality of first MR fingerprint data and the predicted position data to obtain MR fingerprint positioning data of the to-be-positioned point comprises the following steps: constructing a positioning area range with the predicted position data of the to-be-positioned point as the center and a preset error distance as the radius; matching a plurality of second MR fingerprint data that satisfy the positioning area range according to the plurality of first MR fingerprint data; iteratively calculating the confidence between the plurality of second MR fingerprint data and the predicted position data; determining the second MR fingerprint data corresponding to the confidence greater than a preset threshold as third MR fingerprint data; determining the grid position data in the third MR fingerprint data corresponding to a target confidence as the MR fingerprint positioning data of the to-be-positioned point; the target confidence refers to the maximum confidence among the confidences corresponding to the plurality of third MR fingerprint data.

2. The tunnel positioning method of claim 1, wherein, the position data correction based on the MR fingerprint positioning data and the predicted position data to obtain actual positioning data of the to-be-positioned point comprises the following steps: judging whether the MR fingerprint positioning data has a value for rectification; if the MR fingerprint positioning data has a value for rectification, determining actual positioning data of the to-be-positioned point based on the MR fingerprint positioning data and the predicted position data, and correcting navigation parameter errors of the inertial navigation system so that the inertial navigation system predicts position data of a next to-be-positioned point according to the corrected navigation parameter errors.

3. The tunnel positioning method of claim 2, wherein, the determination of actual positioning data of the to-be-positioned point based on the MR fingerprint positioning data and the predicted position data, and the correction of navigation parameter errors of the inertial navigation system, comprises the following steps: subtracting the predicted position data and the MR fingerprint positioning data to obtain a deviation value; performing Kalman filtering based on the deviation value to obtain a filtered error value; subtracting the predicted position data and the filtered error value to obtain actual positioning data of the to-be-positioned point; performing feedback adjustment on navigation parameters output by the inertial navigation system based on the filtered error value to correct navigation parameter errors of the inertial navigation system.

4. The tunnel positioning method of claim 1, wherein, the MR fingerprint library is determined by the following method: acquiring mobile signaling information; determining a communication coverage area based on the mobile signaling information; determining a plurality of base station position points and a plurality of signal strength values corresponding to the plurality of base station position points in the communication coverage area; dividing the communication coverage area into a plurality of grids. determining a plurality of base station location points and a plurality of signal strength values within each grid based on the plurality of base station location points and the plurality of signal strength values in the communication coverage area; generating a unique number of each grid; determining grid location data of each grid; generating MR fingerprint data based on each grid, the unique number of each grid, and the plurality of base station location points and the plurality of signal strength values within each grid, and constructing an MR fingerprint library according to the plurality of MR fingerprint data.

5. The tunnel positioning method according to any one of claims 1-4, characterized in that, The tunnel positioning method further comprises: obtaining MR fingerprint positioning data samples when the user terminal samples are in a plurality of to-be-positioned point samples in the tunnel samples; clustering the plurality of MR fingerprint positioning data samples according to different base stations to obtain a plurality of MR fingerprint positioning data samples of different types; training the plurality of MR fingerprint positioning data samples of different types through a self-encoder to obtain a plurality of denoised MR fingerprint positioning data samples output by the self-encoder; updating the plurality of denoised MR fingerprint positioning data samples to the MR fingerprint library.

6. A tunnel positioning device, characterized by comprises: an acquisition module, configured to acquire a plurality of network parameters reported by a user terminal when the user terminal is in a to-be-positioned point in a tunnel, predicted position data of the to-be-positioned point output by an inertial navigation system, and tunnel location data; a matching module, configured to match a plurality of first MR fingerprint data from a measurement report (MR) fingerprint library based on the plurality of network parameters and the tunnel location data; a similarity analysis module, configured to perform similarity analysis based on the plurality of first MR fingerprint data and the predicted position data to obtain MR fingerprint positioning data of the to-be-positioned point; a correction module, configured to correct position data based on the MR fingerprint positioning data and the predicted position data to obtain actual positioning data of the to-be-positioned point; The similarity analysis based on the plurality of first MR fingerprint data and the predicted position data to obtain the MR fingerprint positioning data of the to-be-positioned point comprises: constructing a positioning area range with the predicted position data of the to-be-positioned point as the center and a preset error distance as the radius; matching a plurality of second MR fingerprint data that satisfy the positioning area range according to the plurality of first MR fingerprint data; iteratively calculating the confidence between the plurality of second MR fingerprint data and the predicted position data; determining the second MR fingerprint data corresponding to the confidence greater than a preset threshold as third MR fingerprint data; determining the grid location data in the third MR fingerprint data corresponding to a target confidence as the MR fingerprint positioning data of the to-be-positioned point; the target confidence refers to the maximum confidence among the confidences corresponding to the plurality of third MR fingerprint data.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein The processor executes the computer program to implement the steps of the tunnel positioning method according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the tunnel positioning method according to any one of claims 1 to 5.

9. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the tunnel positioning method according to any one of claims 1 to 5.

Images