A railway worker positioning method, device, equipment and readable storage medium

Abstract

The present application relates to the technical field of multi-sensor positioning, and relates to a railway worker positioning method, device, equipment and readable storage medium, the method comprising: acquiring first information and second information, the first information comprising satellite signal information collected by a positioning device worn by a railway worker, and the second information comprising inertial navigation signal information collected by the positioning device worn by the railway worker; respectively pre-processing the first information and the second information to obtain pre-processed first information and pre-processed second information; evaluating the pre-processed first information and the pre-processed second information to obtain an evaluation result, the evaluation result comprising an interference degree of electromagnetic interference on a sensor included in the positioning device; and determining the position of the railway worker according to the evaluation result, the present application improving the positioning accuracy of the railway worker in the case of strong electromagnetic signal interference in a railway environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of multi-sensor positioning, in particular to a railway operator positioning method, device, equipment and readable storage medium. BACKGROUND

[0002] In railway operation, it is crucial to ensure the safety of on-site operators. The prior art usually uses satellite positioning technology to position the location of on-site operators in order to determine whether the on-site operators are in a dangerous position. However, in railway operation, there are complex large-scale equipment and strong electromagnetic signal interference, which results in a large error of satellite positioning technology. SUMMARY

[0003] The purpose of the present application is to provide a railway operator method, device, equipment and readable storage medium to improve the above problems.

[0004] In order to achieve the above purpose, the embodiments of the present application provide the following technical solutions:

[0005] On the one hand, the present application provides a railway operator positioning method, which comprises:

[0006] obtaining first information and second information, the first information comprising satellite signal information collected by a positioning device worn by a railway operator, and the second information comprising inertial navigation signal information collected by the positioning device worn by the railway operator;

[0007] respectively pre-processing the first information and the second information to obtain pre-processed first information and pre-processed second information;

[0008] evaluating the pre-processed first information and the pre-processed second information to obtain an evaluation result, the evaluation result comprising the degree of interference of electromagnetic interference on sensors included in the positioning device;

[0009] determining the position of the railway operator according to the evaluation result.

[0010] Secondly, the present application provides a railway operator positioning device, which comprises:

[0011] an acquisition module for acquiring first information and second information, the first information comprising satellite signal information collected by a positioning device worn by a railway operator, and the second information comprising inertial navigation signal information collected by the positioning device worn by the railway operator;

[0012] a first processing module for respectively pre-processing the first information and the second information to obtain pre-processed first information and pre-processed second information;

[0013] a second processing module, configured to evaluate the preprocessed first information and the preprocessed second information to obtain an evaluation result, the evaluation result comprising a degree of interference of electromagnetic interference on a sensor comprised in the positioning device;

[0014] a positioning module, configured to determine a position of the railway worker according to the evaluation result.

[0015] In a third aspect, an embodiment of the present application provides a railway worker positioning device, the device comprising a memory and a processor.

[0016] In a fourth aspect, an embodiment of the present application provides a readable storage medium, the readable storage medium storing a computer program, the computer program being executed by a processor to implement the steps of the above method.

[0017] The present application has the following beneficial effects:

[0018] The present application obtains satellite signal information and inertial navigation signal information, preprocesses the satellite signal information and the inertial navigation signal information respectively to obtain preprocessed first information and preprocessed second information, evaluates the preprocessed first information and the preprocessed second information to determine the degree of interference of electromagnetic interference on the sensor, and adjusts the weight of the sensor according to the degree of interference of the sensor, so as to effectively reduce the influence of electromagnetic interference on the signal, thereby improving the positioning accuracy of the railway worker in a high-noise environment.

[0019] Other features and advantages of the present application will be described in the following description and, in part, will become apparent from the description or be learned by practice of the present application. The objects and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be considered as limiting the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0021] Figure 1 The figure is a railway worker positioning method flowchart described in the embodiments of the present application.

[0022] Figure 2 The figure is a railway worker positioning device topology diagram described in the embodiments of the present application.

[0023] Figure 3 The figure is a structural schematic diagram of the railway worker positioning device described in the embodiment of the present application.

[0024] In the figure, 901 is an acquisition module, 902 is a first processing module, 903 is a second processing module, 904 is a positioning module, 800 is a railway worker positioning device, 801 is a processor, 802 is a memory, 803 is a multimedia assembly, 804 is an I / O interface, and 805 is a communication assembly. DETAILED DESCRIPTION

[0025] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art without creative work based on the embodiments in the present application fall within the scope of protection of the present application.

[0026] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms “first”, “second” and the like are only used to distinguish description, and cannot be understood as indicating or implying relative importance.

[0027] Embodiment 1

[0028] The embodiment provides a railway worker positioning method, and it can be understood that a scene can be laid in the embodiment, for example: when a dangerous situation occurs on a railway, a positioning device worn on the head of a railway worker is used to position the railway worker, to determine whether the railway worker is in a dangerous section, so as to perform a safety warning on the railway worker.

[0029] Referring to Figure 1 , the figure shows that the method includes steps S1, S2, S3 and S4.

[0030] Step S1: acquiring first information and second information, wherein the first information includes satellite signal information collected by a positioning device worn by a railway worker, and the second information includes inertial navigation signal information collected by the positioning device worn by the railway worker;

[0031] In this step, when the railway worker performs the inspection operation on the railway in the section responsible for, the positioning device needs to be worn on the head to collect satellite signal information and inertial navigation signal information to determine the position of the railway worker in real time. The positioning device includes at least two sensors, one for collecting satellite signal information and one for collecting inertial navigation signal information.

[0032] Step S2, respectively, pre-process the first information and the second information to obtain pre-processed first information and pre-processed second information.

[0033] In this step, the pre-processing includes removing outliers, noise, and synchronizing the data collected by the two sensors in time.

[0034] Step S3, evaluating the pre-processed first information and the pre-processed second information to obtain an evaluation result, the evaluation result including the degree of interference of electromagnetic interference on the sensors included in the positioning device.

[0035] In this step, since the pre-processing has removed outliers in the first information and the second information, when evaluating the sensors through the pre-processed first information and the pre-processed second information, the degree of interference of electromagnetic signals on the sensors can be more accurately judged, and the accuracy and reliability of the evaluation result are improved.

[0036] In the step S3, it also includes steps S31, S32, S33 and S34, which specifically include:

[0037] Step S31, obtaining third information, the third information including three pre-processed first information collected in time sequence;

[0038] Step S32, respectively calculating the first characteristic information of each pre-processed first information in the third information, the first characteristic information including signal amplitude;

[0039] Step S33, calculating second characteristic information according to the first characteristic information, the second characteristic information including the average signal amplitude corresponding to the three pre-processed first information;

[0040] Step S34, evaluating according to the second characteristic information and the pre-set third characteristic information to obtain an evaluation result.

[0041] In the embodiment, the satellite signal information collected at three continuous time points is preprocessed to obtain third information, and the signal amplitude corresponding to each satellite signal information is extracted to calculate the average signal amplitude corresponding to the satellite signal information at the three time points. By comparing the average signal amplitude with the signal amplitude of the satellite signal information collected by the sensor without electromagnetic interference, the offset of the signal amplitude can be obtained, and the evaluation result can be obtained. The offset of the signal amplitude can represent the interference degree of the electromagnetic signal on the sensor included in the positioning device.

[0042] In step S4, the position of the railway worker is determined according to the evaluation result.

[0043] In step S4, the position of the railway worker is determined according to the evaluation result.

[0044] In step S41, the evaluation result corresponding to the preprocessed first information and the evaluation result corresponding to the preprocessed second information are respectively sent to the attention mechanism, and the weight of each sensor is calculated.

[0045] In step S41, the position of the railway worker is determined according to the evaluation result.

[0046] In step S411, the historical sample set is obtained, and the historical sample set includes the satellite signal information and the inertial system signal information recorded in the historical information.

[0047] In step S412, the evaluation result corresponding to each satellite signal information and inertial system signal information in the historical sample set is calculated to obtain the sixth information and the seventh information.

[0048] In step S413, an electromagnetic interference weight factor is assigned to each satellite signal information in the historical sample set according to the sixth information, and an electromagnetic interference weight factor is assigned to each inertial navigation signal information in the historical sample set according to the seventh information. Adjust the loss function to obtain an optimized loss function.

[0049] In this step, the optimized loss function is specifically:

[0050]

[0051] In the above formula, L represents the optimized loss function; n represents the number of samples in the historical sample set; w i represents the electromagnetic interference weight factor; y i represents the model output corresponding to the i-th satellite signal information or inertial system signal information, y i ′The target output represents the target output corresponding to the i-th satellite signal information or inertial system signal information, and the target output is the sensor output in a non-electromagnetic interference or ideal electromagnetic interference environment.

[0052] In step S414, the attention mechanism is trained by using the optimized loss function.

[0053] In the embodiment, when the samples are greatly affected by electromagnetic interference, the weight factor is correspondingly increased, so that the model pays more attention to these samples in the optimization process, thereby adjusting the weight of the sensor to adapt to the electromagnetic interference environment, and achieving the purpose of reducing the influence of electromagnetic interference on satellite signals and inertial navigation signals. It should be noted that an update frequency can be set to periodically update the weight of the sensor to ensure the accuracy of positioning.

[0054] In step S42, the sensors are weighted according to the calculated weight of each sensor, and the weighted first information and the weighted second information are obtained.

[0055] In this step, a specific embodiment is that when the sensor collecting satellite signal information is strongly affected by electromagnetic interference, the weight of the sensor is reduced, and when the sensor collecting inertial navigation signal information is weakly affected by electromagnetic interference, the weight of the sensor is increased, thereby obtaining the weighted first information and the weighted second information, so as to effectively improve the positioning accuracy of the railway operating personnel in the electromagnetic interference environment.

[0056] In step S43, the weighted first information and the weighted second information are fused by using complementary filtering to obtain fused information.

[0057] The step S43 further includes steps S431, S432, S433, S434 and S435, which specifically include:

[0058] In step S431, the cutoff frequency of the low-pass filter is determined according to the weight corresponding to the weighted first information, and a first cutoff frequency is obtained.

[0059] In this step, the degree of interference of the electromagnetic signal on the satellite signal information can be determined according to the weight corresponding to the weighted first information. When the degree of interference of the electromagnetic signal on the satellite signal information is serious, a lower cutoff frequency is set as the first cutoff frequency; when the degree of interference of the electromagnetic signal on the satellite signal information is weak, a higher cutoff frequency is set as the first cutoff frequency, so that more satellite signal information is involved in the fusion.

[0060] In step S432, the cutoff frequency of the high-pass filter is determined according to the weight corresponding to the weighted second information, and a second cutoff frequency is obtained.

[0061] In this step, according to the weight corresponding to the weighted second information, the interference degree of the electromagnetic signal to the inertial navigation signal information can be determined, and whether more inertial navigation signal information is allowed to participate in fusion is determined according to the interference degree of the inertial navigation signal information.

[0062] Step S433, filtering the weighted first information according to the first cutoff frequency to obtain fourth information;

[0063] Step S434, filtering the weighted second information according to the second cutoff frequency to obtain fifth information;

[0064] Step S435, fusing the fourth information and the fifth information to obtain fused information.

[0065] In this embodiment, the complementary filtering combines the characteristics of the high-pass filter and the low-pass filter, processes the high-frequency signal and the low-frequency signal respectively, and then fuses them, so as to realize the complementary advantages of different frequency signals, and determine the first cutoff frequency of the low-pass filter and the second cutoff frequency of the high-pass filter according to the interference degrees of the electromagnetic signal to the satellite signal and the inertial navigation signal, so as to reduce the influence of electromagnetic interference on the fused information, thereby improving the positioning accuracy of the railway operating personnel.

[0066] Step S44, determining the position of the railway operating personnel according to the fused information.

[0067] After the step S4, the steps S5, S6, S7, S8 and S9 are further included, which specifically include:

[0068] Step S5, acquiring railway design information;

[0069] Step S6, determining tunnel position information and tunnel length information according to the railway design information;

[0070] Step S7, determining the installation position of the laser radar according to the tunnel position information;

[0071] Step S8, determining the installation number of the laser radar according to the tunnel length information;

[0072] Step S9, spacing the laser radars in the tunnel according to the installation position of the laser radar and the installation number of the laser radar.

[0073] In the embodiment, since the railway environment belongs to a complex environment, not only there are complex large equipment and strong electromagnetic signal interference, but also there are some shielding environments such as tunnels. In the tunnel, not only there is electromagnetic interference, but also there is shielding, so that the satellite signal cannot accurately detect the position of the railway operating personnel in the tunnel. Therefore, according to the length information of the tunnel, a plurality of laser radars are arranged in the tunnel in the embodiment, so that the electromagnetic interference can be ignored, and the position of the railway operating personnel in the tunnel can be accurately positioned. When the railway operating personnel is located outside the tunnel, the first information and the second information are collected to realize accurate real-time positioning of the railway operating personnel. When the railway operating personnel enters the tunnel, the position of the railway operating personnel is positioned in real time by the laser radar, so that accurate positioning of the operating personnel in the whole complex railway environment is realized.

[0074] The step S9 further includes a step S91, a step S92, a step S93, a step S94 and a step S95, which specifically include:

[0075] The step S91 is acquiring point cloud data.

[0076] In the step, the point cloud data is collected by the laser radar arranged in the tunnel.

[0077] The step S92 is sending the point cloud data to a denoising model to obtain denoised point cloud data.

[0078] In the step, the point cloud data is denoised by using the denoising model, which is a technical solution known to those skilled in the art, and will not be described here.

[0079] The step S93 is extracting feature information in the denoised point cloud data to obtain fourth feature information.

[0080] The step S93 further includes a step S931, a step S932, a step S933 and a step S934, which specifically include:

[0081] The step S931 is voxelizing the denoised point cloud data to obtain eighth information.

[0082] The step S932 is extracting feature information in the eighth information to obtain voxel feature information, and the voxel feature information includes voxel features of different scales.

[0083] The step S933 is performing double-value interpolation processing on the denoised point cloud data to obtain fifth feature information.

[0084] In the step, the fifth feature information is bird's eye view feature information, and the bird's eye view feature information can reflect the relationship between the target object and the space, so as to quickly detect and position the target in the plane.

[0085] Step S934, fuse the voxel feature information and the fifth feature information to obtain the fourth feature information.

[0086] In this step, by fusing voxel features of different scales and bird's eye view feature information, the expression ability of point cloud data on the bird's eye view can be effectively improved, thereby further improving the understanding of the scene and the accuracy of railway worker detection.

[0087] Step S94, sending the fourth feature information to a target detection model to obtain target object information, the target object information including workers in the tunnel;

[0088] In this step, the target detection model includes a two-dimensional convolution network and a multi-task detection head network, wherein the two-dimensional convolution network includes three convolution blocks, one of which is composed of four convolution layers, and two of which are composed of six convolution layers. The first layer of each convolution block is a convolution layer with a step of 2, which samples the feature map to half of the original, followed by several convolution layers with a step of 1. The fourth feature information is sent to the two-dimensional convolution network for three downsampling operations to obtain feature information at different levels, which is then fused to make the fused features include both deep abstract features and shallow shape and contour features, so as to have stronger feature expression ability and improve the accuracy of railway worker detection.

[0089] Step S95, determining the position of the target object according to the target object information.

[0090] Since the tunnel includes but is not limited to obstacles such as falling rocks, collapsed objects, and faulty vehicles, in this embodiment, the voxel features and bird's eye view features of the point cloud data are extracted and fused, and then sent to the target detection model to realize accurate detection of railway workers, and then the corresponding point cloud data can be used to realize accurate positioning of the railway workers.

[0091] Embodiment 2:

[0092] As shown in Figure 2 The present embodiment provides a railway worker positioning device, which comprises an acquisition module 901, a first processing module 902, a second processing module 903, and a positioning module 904, and specifically comprises:

[0093] The acquisition module 901 is configured to acquire first information and second information, wherein the first information includes satellite signal information collected by a positioning device worn by a railway worker, and the second information includes inertial navigation signal information collected by the positioning device worn by the railway worker.

[0094] The first processing module 902 is used to preprocess the first information and the second information respectively to obtain the preprocessed first information and the preprocessed second information;

[0095] The second processing module 903 is used to evaluate the preprocessed first information and the preprocessed second information to obtain an evaluation result, the evaluation result including the degree of electromagnetic interference to the sensors included in the positioning device.

[0096] The positioning module 904 is used to determine the location of railway workers based on the evaluation results.

[0097] It should be noted that the specific manner in which each module performs its operation in the apparatus described in the above embodiments has been described in detail in the embodiments of the method, and will not be elaborated here.

[0098] Example 3:

[0099] Corresponding to the above method embodiments, this embodiment also provides a railway worker positioning device. The railway worker positioning device described below and the railway worker positioning method described above can be referred to each other.

[0100] Figure 3 This is a block diagram illustrating a railway worker positioning device 800 according to an exemplary embodiment. Figure 3 As shown, the railway worker positioning device 800 may include: a processor 801 and a memory 802. The railway worker positioning device 800 may also include one or more of the following: a multimedia component 803, an I / O interface 804, and a communication component 805.

[0101] The processor 801 is configured to control overall operations of the railway worker positioning device 800 to complete all or part of the steps of the railway worker positioning method described above. The memory 802 is configured to store various types of data to support the operations of the railway worker positioning device 800, which can include, for example, instructions for any application or method operating on the railway worker positioning device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 802 or transmitted through the communication component 805. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 805 is configured to enable wired or wireless communication between the railway worker positioning device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include a Wi-Fi module, a Bluetooth module, an NFC module.

[0102] In an example embodiment, the railroad worker positioning device 800 can be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements for executing the railroad worker positioning method described above.

[0103] In another example embodiment, a computer-readable storage medium including program instructions that, when executed by a processor, implement the steps of the railroad worker positioning method described above is also provided. For example, the computer-readable storage medium can be the memory 802 described above including program instructions that are executable by the processor 801 of the railroad worker positioning device 800 to complete the railroad worker positioning method described above.

[0104] Embodiment 4:

[0105] Corresponding to the method embodiments above, a readable storage medium is also provided in this embodiment, and the readable storage medium described below can be referred to in correspondence with the railroad worker positioning method described above.

[0106] A readable storage medium, on which a computer program is stored, the computer program being executable by a processor to implement the steps of the railroad worker positioning method of the method embodiments described above.

[0107] The readable storage medium can specifically be a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or various readable storage media that can store program codes.

[0108] The above only describes preferred embodiments of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0109] The above merely illustrates the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for locating railway workers, characterized in that, include: Acquire first information and second information, wherein the first information includes satellite signal information collected by the positioning device worn by railway workers, and the second information includes inertial navigation signal information collected by the positioning device worn by railway workers; The first information and the second information are preprocessed respectively to obtain the preprocessed first information and the preprocessed second information; The preprocessed first information and the preprocessed second information are evaluated to obtain an evaluation result, which includes the degree of electromagnetic interference to the sensors included in the positioning device. After determining the location of railway workers based on the assessment results, the process also includes: Obtain railway design information; The tunnel location and length information are determined based on the railway design information. The installation location of the lidar is determined based on the tunnel location information; The number of lidar units to be installed is determined based on the tunnel length information; The lidar is installed at intervals within the tunnel according to its installation location and the number of lidars, including: Acquire point cloud data; The point cloud data is sent to the denoising model to obtain denoised point cloud data; The feature information is extracted from the denoised point cloud data to obtain the fourth feature information; The fourth feature information is sent to the target detection model to obtain target object information, which includes workers inside the tunnel. The location of the target object is determined based on the point cloud data corresponding to the target object information.

2. The railway worker positioning method according to claim 1, characterized in that, The preprocessed first information and the preprocessed second information are evaluated to obtain the evaluation result, including: Obtain third information, which includes three preprocessed pieces of first information collected in chronological order; Calculate the first feature information for each of the preprocessed first information in the third information, where the first feature information includes the signal amplitude. The second feature information is calculated based on the first feature information, and the second feature information includes the average signal amplitude corresponding to the three preprocessed first information. An evaluation result is obtained by evaluating the second feature information and the preset third feature information. The preset third feature information is the signal amplitude of the satellite signal information collected by the sensor when there is no electromagnetic interference.

3. The railway worker positioning method according to claim 1, characterized in that, The location of railway workers is determined based on the assessment results, including: The evaluation results corresponding to the preprocessed first information and the evaluation results corresponding to the preprocessed second information are sent to the attention mechanism respectively to calculate the weight of each sensor; The sensors are weighted according to the calculated weight of each sensor to obtain weighted first information and weighted second information; The weighted first information and the weighted second information are fused using complementary filtering to obtain fused information; The location of railway workers is determined based on the fused information.

4. The railway worker positioning method according to claim 3, characterized in that, The weighted first information and the weighted second information are fused using complementary filtering, including: The cutoff frequency of the low-pass filter is determined based on the weights corresponding to the weighted first information, thus obtaining the first cutoff frequency; The cutoff frequency of the high-pass filter is determined based on the weights corresponding to the weighted second information, thus obtaining the second cutoff frequency; The weighted first information is filtered according to the first cutoff frequency to obtain the fourth information; The weighted second information is filtered according to the second cutoff frequency to obtain the fifth information; The fourth and fifth pieces of information are then fused to obtain the fused information.

5. The railway worker positioning method according to claim 3, characterized in that, The evaluation results corresponding to the preprocessed first information and the evaluation results corresponding to the preprocessed second information are respectively sent to the attention mechanism, including: Obtain a historical sample set, which includes satellite signal information and inertial system signal information recorded in historical information; The evaluation results corresponding to each satellite signal information and inertial system signal information in the historical sample set are calculated to obtain the sixth and seventh information. Based on the sixth information, an electromagnetic interference weight factor is assigned to each satellite signal information included in the historical sample set, and based on the seventh information, an electromagnetic interference weight factor is assigned to each inertial navigation signal information included in the historical sample set. The loss function is then adjusted to obtain the optimized loss function. The attention mechanism is trained using the optimized loss function.

6. A railway worker positioning device, using the railway worker positioning method as described in claim 1, characterized in that, include: The acquisition module is used to acquire first information and second information. The first information includes satellite signal information collected by the positioning device worn by railway workers, and the second information includes inertial navigation signal information collected by the positioning device worn by railway workers. The first processing module is used to preprocess the first information and the second information respectively to obtain the preprocessed first information and the preprocessed second information; The second processing module is used to evaluate the preprocessed first information and the preprocessed second information to obtain an evaluation result, which includes the degree of electromagnetic interference to the sensors included in the positioning device. A positioning module is used to determine the location of railway workers based on the evaluation results.

7. A railway worker positioning device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the railway worker positioning method as described in any one of claims 1 to 5 when executing the computer program.

8. A readable storage medium, characterized in that: The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the railway worker positioning method as described in any one of claims 1 to 5.

Images