Cable path diagram analysis model training method, analysis method, device and medium

Abstract

The application relates to a cable path map analysis model training method and device, an analysis method and device and a medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring at least one first railway signal cable path map; intercepting at least one first screenshot containing a railway signal device from each first railway signal cable path map, and generating a corresponding railway signal device position mask map according to the first screenshot; determining the associated cable path map of the railway signal device in each first screenshot in the corresponding first railway signal cable path map; training a preset image segmentation network based on the railway signal device position mask map, the associated cable path map and the first railway signal cable path map corresponding to each first screenshot, so as to obtain a cable path map analysis model. The application has the effect of improving fault troubleshooting efficiency.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, specifically to a method for training an analytical model of a cable routing map, an analytical method, an apparatus, and a medium. Background Technology

[0002] A cable routing diagram is an engineering drawing that details the physical route and layout of cables or wires within a specific area. The most common type of cable routing diagram is the railway signal cable routing diagram, which describes the layout, connection, and transmission paths of various signal cables in a railway signaling system. This includes different railway signaling devices that are connected to each other. Railway signaling devices refer to various devices used to control and monitor train operation, ensuring the safe and efficient operation of trains.

[0003] Currently, railway signaling equipment occasionally malfunctions. When this happens, the equipment becomes unusable, directly impacting railway traffic safety. The common approach is to quickly determine the cause of the malfunction by tracing the cable routes. This method requires experienced personnel to locate the necessary cable routes from engineering drawings. However, the intricate network of cable routes in engineering drawings makes identifying the faulty cable route time-consuming, resulting in low troubleshooting efficiency. Summary of the Invention

[0004] To improve the efficiency of fault diagnosis, this application provides a method, analytical method, device and medium for training an analytical model of a cable routing diagram.

[0005] The first aspect of this application provides a method for training an analytical model of a cable path diagram, specifically including: Obtain at least one first railway signal cable route map, the first railway signal cable route map including different railway signal devices that are connected to each other; Take at least one first screenshot containing railway signal equipment from each of the first railway signal cable route maps, and generate a corresponding railway signal equipment location mask map based on the first screenshot; Determine the associated cable path diagram of each railway signaling device in the first screenshot in the corresponding first railway signaling cable path diagram. The associated cable path diagram is the part of the cable path diagram that is most associated with the corresponding railway signaling device when an anomaly occurs. Based on the railway signal equipment location mask map, associated cable path map, and first railway signal cable path map corresponding to each of the first screenshots, a preset image segmentation network is trained to obtain a cable path map parsing model. The cable path map parsing model is a model that outputs the associated cable path map of the corresponding railway signal equipment based on the input railway signal cable path map and railway signal equipment location mask map.

[0006] By adopting the above technical solution, after obtaining the first railway signal cable route map, a first screenshot containing railway signal equipment is extracted from the first railway signal cable route map, and then the corresponding railway signal equipment location mask map is determined, thereby representing the location information of the railway signal equipment in the corresponding first railway signal cable route map. Further, the railway signal equipment location mask map corresponding to a single first screenshot, the first railway signal cable route map, and the associated cable route map are used as training data to train the image segmentation network. This allows the network to continuously learn and acquire the ability to segment the associated cable route map corresponding to the railway signal equipment from the first railway signal cable route map, ultimately obtaining a cable route map parsing model. Once a railway signal equipment malfunctions, simply inputting the location mask map of the malfunctioning railway signal equipment and the corresponding railway signal cable route map into this cable route map parsing model can quickly determine the cable route that needs to be investigated, improving fault diagnosis efficiency.

[0007] Optionally, training a preset image segmentation network based on the railway signaling equipment location mask map, associated cable path map, and first railway signaling cable path map corresponding to each of the first screenshots specifically includes: The first railway signal cable route map corresponding to each of the first screenshots is converted into an input cable route map in image format, and the size of the input cable route map is adjusted to a first preset size to obtain the corresponding first input data; Adjust the size of the railway signal equipment location mask image corresponding to each of the first screenshots to the first preset size to obtain the corresponding second input data; The first input data and the second input data corresponding to the same first screenshot are concatenated to obtain the final input data. Based on the final input data and the associated cable path map corresponding to each of the first screenshots, the preset image segmentation network is trained.

[0008] By adopting the above technical solution, the first railway signal cable route map is converted into an image format and the image size is adjusted to a first preset size. At the same time, the size of the railway signal equipment location mask map corresponding to the first screenshot is also adjusted to the same first preset size. Finally, the first input data and the second input data after size adjustment are concatenated to obtain the final input data. This final input data is then input into the cable route map analysis model for training, thereby improving the training effect of the cable route map analysis model.

[0009] A second aspect of this application provides a method for parsing cable routing diagrams, specifically including: Obtain a second railway signal cable path map containing abnormal railway signal equipment, obtain a cable path map analytical model using the cable path map analytical model training method described in the first aspect above, and obtain a target equipment location mask map corresponding to the abnormal railway signal equipment; The second railway signal cable route map and the target equipment location mask map are preprocessed to obtain the target input data; The target input data is input into the cable path map analysis model to obtain the target associated cable path map corresponding to the abnormal railway signal equipment; The target associated cable route map is overlaid onto the second railway signal cable route map and highlighted.

[0010] By employing the above technical solution, the trained cable path map analysis model is invoked. The preprocessed second railway signal cable path map containing the abnormal railway signal equipment and the target equipment location mask map are then input into this model. The cable path map analysis model then predicts the target associated cable path map corresponding to the abnormal railway signal equipment. Finally, the target associated cable path map is superimposed onto the second railway signal cable path map. This allows personnel to determine the cable path requiring troubleshooting based on the target associated cable path map, eliminating the need to manually search through the complex cable paths in the second railway signal cable path map and improving troubleshooting efficiency.

[0011] Optionally, obtaining the target equipment location mask map corresponding to the abnormal railway signaling equipment specifically includes: Obtain at least one third railway signal cable route map, and extract at least one second screenshot that does not contain railway signal equipment and one third screenshot that contains railway signal equipment from each of the third railway signal cable route maps; Each of the second screenshots and each of the third screenshots are determined as an image binary classification dataset, and a preset binary classification neural network is trained using the image binary classification dataset to obtain the final binary classification network after training and store it in a preset database. The final binary classification network can determine whether the input screenshot contains railway signal equipment. An initial screenshot corresponding to the abnormal railway signal equipment is extracted from the second railway signal cable path map, and the initial screenshot is input into the final binary classification network to obtain the corresponding output result; Based on the output results, determine whether the corresponding initial screenshot contains railway signal equipment. If so, generate a target equipment location mask image corresponding to the abnormal railway signal equipment based on the initial screenshot. If not, repeat the step of extracting the initial screenshot corresponding to the abnormal railway signaling equipment from the second railway signaling cable route map.

[0012] By adopting the above technical solution, if the output result determines that the initial screenshot contains railway signal equipment, it means that the initial screenshot successfully captured the abnormal railway signal equipment. Then, the corresponding target equipment location mask map is determined. Conversely, if the initial screenshot does not contain this railway signal equipment, it means that the initial screenshot failed to capture the abnormal railway signal equipment. In this case, the step of capturing the initial screenshot corresponding to the abnormal railway signal equipment from the second railway signal cable path map is repeated. The newly captured initial screenshot is then input into the final binary classification network. The output result is used to determine whether the initial screenshot contains the abnormal railway signal equipment, thereby making the determined target equipment location mask map more accurate.

[0013] Optionally, the preprocessing of the second railway signal cable route map and the target equipment location mask map to obtain target input data specifically includes: The second railway signal cable route map is converted into an image format and its size is adjusted to a second preset size to obtain the first target input data; The size of the target device location mask is adjusted to the second preset size to obtain the second target input data. The first target input data and the second target input data are then concatenated to obtain the target input data.

[0014] By adopting the above technical solution, the second railway signal cable path map is converted into an image format and the image size is adjusted to a second preset size. At the same time, the size of the target equipment location mask map is also adjusted to the same second preset size. Finally, the first target input data and the second target input data after size adjustment are concatenated to obtain the target input data. This target input data is then input into the cable path map analysis model, thereby improving the performance of the cable path map analysis model and making the prediction of the associated cable path map of abnormal railway signal equipment more accurate.

[0015] Optionally, the method further includes: Obtain historical anomalies of railway signaling equipment that have experienced anomalies, count the first occurrence count of each historical anomaly, and select the historical anomaly with the highest first occurrence count from the historical anomalies in descending order to determine it as a likely anomaly. Obtain the abnormal environment factors of the historical associated cable path map corresponding to the occurrence of a single abnormality in the historical railway signal equipment, and count the second occurrence number of each of the abnormal environment factors. The abnormal environment factor is the abnormal environment of the cable corresponding to the associated cable path map of the identified fault. According to the order of the second occurrence frequency from largest to smallest, select the second number of abnormal environmental factors from each of the abnormal environmental factors and determine them as the corresponding easily induced abnormal factors that are prone to abnormality. Calculate the first weight of each of the easily occurring anomalies and the second weight of each corresponding easily induced anomaly factor. The first weight is the ratio of the first occurrence number of each easily occurring anomaly to the sum of the first occurrence numbers of all easily occurring anomalies. The second weight is the ratio of the second occurrence number of a single easily induced anomaly factor corresponding to the easily occurring anomaly to the sum of the second occurrence numbers of all corresponding easily induced anomaly factors. When the target anomaly of the abnormal railway signaling equipment is the easily occurring anomaly, the target associated cable path map is verified based on the first weight of the target anomaly and the second weight of the easily induced anomaly factor in the abnormal environmental factors of the target associated cable path map.

[0016] By adopting the above technical solution, the more frequent the first occurrence, the more likely the railway signaling equipment is to exhibit the corresponding historical anomaly. Then, following the order of the first occurrence frequency from largest to smallest, the historical anomalies with the highest frequency are selected as likely anomalies, i.e., anomalies that are prone to occur in railway signaling equipment. Furthermore, the more frequent the second occurrence, the more likely the cables in the corresponding historical path diagram are to have corresponding anomalous environmental factors. Further, following the order of the second occurrence frequency from largest to smallest, the anomalous environmental factors with the highest frequency are selected, i.e., factors that easily induce anomalies. Finally, based on the first weight of the target anomaly and the second weight of the easily induced anomaly factors corresponding to the target associated cable path diagram, the rationality of troubleshooting through the target associated cable path diagram is analyzed, thereby achieving the verification of the target associated cable path diagram and improving the efficiency of troubleshooting.

[0017] Optionally, the verification of the target-related cable path map based on the first weight of the target anomaly and the second weight of each easily induced anomaly factor in the anomaly environmental factors of the target-related cable path map specifically includes: Calculate the first weight of the target anomaly and the second weight of each easily induced anomaly factor in the abnormal environmental factors of the target associated cable path map to obtain the corresponding weight product; The weights are multiplied together to obtain a weight product sum, and the weight product sum is compared with a preset product sum threshold. If the sum of the weighted products is greater than the product sum threshold, then the verification of the target associated cable path map is determined to be successful, and the target cable path corresponding to the target associated cable path map is investigated.

[0018] By adopting the above technical solution, when the target anomaly of the abnormal railway signaling equipment is a likely anomaly, the product of the first weight of the target anomaly and the second weight of each easily induced anomaly factor in the abnormal environmental factors of the target associated cable path diagram is calculated. The larger the weight product, the greater the probability that the target anomaly is caused by the corresponding easily induced anomaly factor. Finally, the weight products are summed to obtain the weight product sum. The larger the weight product sum, the greater the possibility that the target anomaly is caused by the easily induced anomaly factor in the abnormal environmental factors of the target associated cable path diagram. The weight products are compared with a preset product sum threshold. If the weight product sum is greater than the product sum threshold, it indicates that the target anomaly is more likely to be caused by the easily induced anomaly factor in the abnormal environmental factors of the target associated cable path diagram. This indicates that the target cable path in the target associated cable path diagram is indeed the cable path that needs to be investigated. Therefore, the target associated cable path diagram is verified as passed. By investigating the target cable path in this target associated cable path diagram, the fault point can be found with a high probability, improving the efficiency of the investigation.

[0019] Optionally, the step of investigating the target cable path corresponding to the target associated cable path map specifically includes: At least one target cable segment is determined from the target cable path corresponding to the target associated cable path map. The target cable segment is a part of the cable in the target cable path that contains factors that are prone to induce abnormalities. The investigation priority of the corresponding target cable segment is determined based on the weighted product. The larger the weighted product, the higher the investigation priority of the corresponding target cable segment. The target cable segments in the target cable path are investigated sequentially according to the investigation priority from high to low.

[0020] By adopting the above technical solution, the investigation priority of the corresponding target cable segment is determined based on the weighted product of the factors that are prone to causing anomalies in the target cable path. The larger the weighted product, the greater the probability that the corresponding factor will cause an anomaly, and the higher the investigation priority of the corresponding target cable segment. Finally, according to each investigation priority, the corresponding target cable segments in the target cable path are investigated sequentially, thereby further improving the efficiency of troubleshooting faults that cause target anomalies.

[0021] A third aspect of this application provides a training apparatus for an analytical model of a cable path diagram, specifically comprising: The information acquisition module is used to acquire at least one first railway signal cable route map, wherein the first railway signal cable route map includes different railway signal devices that are connected to each other; The mask determination module is used to extract at least one first screenshot containing railway signal equipment from each of the first railway signal cable route maps, and generate a corresponding railway signal equipment location mask map based on the first screenshot. The route determination module is used to determine the associated cable route diagram of each railway signal device in the first screenshot in the corresponding first railway signal cable route diagram. The associated cable route diagram is the part of the cable route diagram that is most associated with the corresponding railway signal device when an anomaly occurs. The model training module is used to train a preset image segmentation network based on the location mask map of railway signal equipment, the associated cable path map, and the first railway signal cable path map corresponding to each of the first screenshots, so as to obtain a cable path map parsing model. The cable path map parsing model is a model that outputs the associated cable path map of the corresponding railway signal equipment based on the input railway signal cable path map and railway signal equipment location mask map.

[0022] By adopting the above technical solution, the information acquisition module obtains the first railway signal cable route map, the mask determination module generates the corresponding railway signal equipment location mask map based on the first screenshot, then the route determination module determines the associated cable route map corresponding to the railway signal equipment in the first screenshot, and finally the image segmentation network is trained based on the railway signal equipment location mask map, associated cable route map and the first railway signal cable route map corresponding to the first screenshot to obtain the cable route map parsing model.

[0023] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when loaded and executed by a processor, performs the steps of the method described in any one of the first aspects.

[0024] In summary, this application includes at least one of the following beneficial technical effects: A first screenshot containing railway signaling equipment is extracted from a first railway signaling cable path map, and then the corresponding railway signaling equipment location mask map is determined, thereby representing the location information of the railway signaling equipment in the corresponding first railway signaling cable path map. Furthermore, the railway signaling equipment location mask map corresponding to a single first screenshot, the first railway signaling cable path map, and the associated cable path map are used as training data to train an image segmentation network. This allows the network to continuously learn and acquire the ability to segment the associated cable path map corresponding to the railway signaling equipment from the first railway signaling cable path map, ultimately obtaining a cable path map analysis model. Once a railway signaling equipment malfunctions, simply inputting the location mask map of the malfunctioning railway signaling equipment and the corresponding railway signaling cable path map into this cable path map analysis model quickly determines the cable path that needs to be investigated, improving fault diagnosis efficiency. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating a method for training an analytical model of a cable path diagram according to an embodiment of this application. Figure 2 This is a flowchart illustrating a method for parsing cable routing diagrams provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a cable path diagram analytical model training device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a cable path diagram analysis device provided in an embodiment of this application; Figure 5 This is a schematic diagram of another cable path map parsing device provided in an embodiment of this application.

[0026] Figure labeling: 11. Information acquisition module; 12. Mask determination module; 13. Path determination module; 14. Model training module; 21. Data acquisition module; 22. Image processing module; 23. Model prediction module; 24. Path overlay module; 25. Path verification module. Detailed Implementation

[0027] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0028] In the description of the embodiments of this application, words such as "illustrative," "for example," or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "illustrative," "for example," or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of words such as "illustrative," "for example," or "for example" is intended to present the relevant concepts in a specific manner.

[0029] In the description of the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, B existing alone, or A and B existing simultaneously. Furthermore, unless otherwise stated, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0030] See Figure 1 This application discloses a flowchart illustrating a method for training an analytical model of cable path diagrams. This method can be implemented using a computer program or run on a cable path diagram analytical model training device based on the von Neumann architecture. The computer program can be integrated into an application or run as a standalone utility application, specifically including: S101: Obtain at least one first railway signal cable route map.

[0031] Specifically, the first railway signal cable routing diagram is a schematic diagram describing the layout, connection, and transmission path of various signal cables in a railway signaling system. It is crucial for maintenance personnel to troubleshoot and modify lines. In this embodiment, the first railway signal cable routing diagram includes different railway signaling devices that are interconnected. The diagram can be an electronic drawing in Computer-Aided Design (CAD) format; in other embodiments, it can also be an electronic drawing in vector graphics format. Railway signaling devices refer to various devices used to control and monitor train operation, ensuring safe and efficient train travel. Exemplarily, railway signaling devices can include signals, switch machines, and track circuits, etc.

[0032] Furthermore, this application discloses a method for training an analytical model of a cable routing map, in which the execution entity is a server. The server can be an independent physical server, a server cluster consisting of multiple physical servers, or a distributed system. The server and the terminal are directly or indirectly connected via wired or wireless networks. Further, a feasible method for obtaining a first railway signal cable routing map is as follows: personnel upload first railway signal cable routing maps corresponding to different railway projects via a terminal, and the terminal sends each first railway signal cable routing map to the server, which ultimately obtains at least one first railway signal cable routing map. In other embodiments, at least one first railway signal cable routing map corresponding to a single railway project can also be sent to the server via a terminal. The terminal can be a smartphone or a personal computer.

[0033] S102: Extract at least one first screenshot containing railway signal equipment from each of the first railway signal cable route diagrams, and generate a corresponding railway signal equipment location mask based on the first screenshot.

[0034] Specifically, after obtaining the first railway signal cable route map, random screenshots are taken from each of the first railway signal cable route maps. The size of the screenshots is a preset fixed size. One feasible way to take the first screenshot is as follows: a person sends a screenshot command to the server through a terminal. The screenshot command includes the area to be screenshotted from the first railway signal cable route map (the area containing railway signal equipment). After receiving the screenshot command, the server uses a preset screenshot tool to take at least one first screenshot containing railway signal equipment from each of the first railway signal cable route maps. The screenshot tool can be the Snipaste tool or the ShareX tool. In other embodiments, a person can also take the first screenshot of each first railway signal cable route map through a terminal and finally send it to the server through the terminal.

[0035] Furthermore, a corresponding railway signal equipment location mask is generated based on each first screenshot, that is, a location mask of the railway signal equipment contained in each first screenshot, thereby representing the location information of the railway signal equipment in the corresponding first railway signal cable route map. One feasible generation method is to input the first screenshot and the corresponding first railway signal cable route map into a preset OpenCV tool to generate the corresponding railway signal equipment location mask.

[0036] S103: Determine the associated cable path diagram of the railway signal equipment in each first screenshot in the corresponding first railway signal cable path diagram. The associated cable path diagram is the part of the cable path diagram that is most associated with the corresponding railway signal equipment when an anomaly occurs.

[0037] Specifically, after determining the location mask map of the railway signaling equipment corresponding to each first screenshot, it is necessary to determine the associated cable path map of the railway signaling equipment in the first screenshot. The associated cable path map is the part of the cable path map that is most closely related to the corresponding railway signaling equipment when an anomaly occurs. That is, when a fault point appears in the cable in the associated cable path map, it is most likely to cause an anomaly in the corresponding railway signaling equipment. One feasible determination method is to obtain the historical cable path map of a single railway signaling equipment in the historical anomaly investigation record from the cable path investigation record, filter out the historical cable path map that successfully investigated the fault point from each historical cable path map, and count the occurrence frequency of each successfully investigated historical cable path map. The historical cable path map that appears most frequently is determined as the associated cable path map of the corresponding railway signaling equipment. In other embodiments, a path map selection command sent by the terminal for a single first railway signaling cable path map can also be received, and the part of the cable path map corresponding to the path map selection command in the first railway signaling cable path map can be determined as the associated cable path map of the railway signaling equipment. For example, the associated cable routing diagram of railway signaling equipment A includes railway signaling equipment A itself. It should be noted that the partial cable routing diagram is a portion of the cable routes in the corresponding first railway signaling cable routing diagram. A cable route refers to the specific path of a cable from one connection point to another, connecting at least one railway signaling device. The first railway signaling cable routing diagram includes several different cable routes.

[0038] S104: Based on the railway signal equipment location mask map, associated cable path map and first railway signal cable path map corresponding to each first screenshot, the preset image segmentation network is trained to obtain the cable path map parsing model.

[0039] Specifically, after determining the location mask map of the railway signaling equipment and the associated cable path map corresponding to each first screenshot, the first railway signaling cable path map corresponding to each first screenshot is converted into an input cable path map in image format. In this embodiment, the image format can be JPG, and in other embodiments, it can be PNG. Next, the size of the input cable path map is adjusted to a first preset size to obtain the corresponding first input data. In this embodiment, the first preset size can be (1024, 1024), and in other embodiments, it can be (512, 512), thereby meeting the input size requirements of the deep learning model as much as possible and improving the performance of the deep learning model. Further, the size of the railway signaling equipment location mask map corresponding to the same first screenshot is also adjusted to the first preset size to obtain the corresponding second input data. Further, the first input data and the second input data corresponding to the same first screenshot are concatenated using a preset concatenation function to obtain the final input data. Further, the final input data corresponding to each first screenshot and the associated cable path map are aggregated into a training dataset. This training dataset is then divided into a training set, a validation set, and a test set according to a first partitioning ratio. The preset image segmentation network is trained using the training set, validation set, and test set to obtain the cable path map parsing model. The first partitioning ratio can be 7:2:1 or 6:3:1. In other embodiments, the training dataset can also be divided into a training set and a test set according to a second partitioning ratio, which can be 8:2 or 7:3. The railway signal cable path map and the railway signal equipment location mask map are input into this cable path map parsing model, and the model can output the associated cable path map of the corresponding railway signal equipment. Additionally, the image segmentation network can be a UNET network; in other embodiments, it can be a DeepLab network. The image segmentation network mainly utilizes deep learning technology to achieve the image segmentation task.

[0040] It should be noted that when railway signaling equipment malfunctions, in order to quickly determine the cable path that needs to be investigated and improve the efficiency of fault diagnosis, the railway signaling cable path diagram and the location mask diagram of the malfunctioning railway signaling equipment are input into this cable path diagram analysis model, thereby quickly determining the cable path that needs to be investigated, i.e., associating the cable path diagram.

[0041] See Figure 2 This application discloses a flowchart illustrating a method for parsing cable routing diagrams. This method can be implemented using a computer program or run on a cable routing diagram parsing device based on the von Neumann architecture. The computer program can be integrated into an application or run as a standalone utility application, specifically including: S201: Obtain a second railway signal cable path map containing the abnormal railway signal equipment, a cable path map analytical model obtained by the cable path map analytical model training method in any of the above embodiments, and obtain a target equipment location mask map corresponding to the abnormal railway signal equipment.

[0042] Specifically, after the cable routing diagram analysis model is determined, if there is an abnormal railway signaling device, in order to avoid affecting railway traffic safety, it is necessary to quickly investigate the cable routing and rapidly determine the fault point. Therefore, obtaining a second railway signaling cable routing diagram containing this abnormal railway signaling device is crucial. One feasible method is for railway maintenance personnel to send a CAD electronic drawing of the overall cable routing diagram containing this abnormal railway signaling device—that is, the second railway signaling cable routing diagram—to the server via a terminal. The server then obtains the second railway signaling cable routing diagram. Further, the target device location mask map corresponding to this abnormal railway signaling device is obtained; that is, a mask map representing the location information of the abnormal railway signaling device in the second railway signaling cable routing diagram. One feasible method is as follows: First, extract an initial screenshot corresponding to the abnormal railway signaling device from the second railway signaling cable path map. Then, call a preset final binary classification network from the database, input the initial screenshot into the final binary classification network, and obtain the output result. In this embodiment, the output result is the predicted probability value that the initial screenshot contains the abnormal railway signaling device, with a value range of [0,1]. If the output result exceeds a preset threshold value, the threshold value is 0.5. For example, if the output result is 0.8, exceeding the threshold value of 0.5, then it is determined that the corresponding initial screenshot contains the abnormal railway signaling device. Then, input this initial screenshot and the second railway signaling cable path map into a preset OpenCV tool to obtain the corresponding target device location mask map. Conversely, if the output result does not exceed the threshold value, it means that the initial screenshot does not contain the abnormal railway signaling device. Then, repeat the step of extracting the initial screenshot corresponding to the abnormal railway signaling device from the second railway signaling cable path map, and input the newly extracted initial screenshot into the final binary classification network. Determine whether the initial screenshot contains the abnormal railway signaling device based on the output result. The final binary classification network can determine whether the input screenshot contains railway signal equipment. In other embodiments, the size of the initial screenshot can be adjusted to (32,32) before being input into the final binary classification network, thereby improving the performance of the model.

[0043] Further, the feasible method for determining the final binary classification network is as follows: At least one third railway signal cable route map is obtained, and at least one second screenshot (not containing railway signal equipment) and one third screenshot (containing railway signal equipment) are extracted from each of the third railway signal cable route maps. See steps S101 and S102 for details, which will not be repeated here. Then, each second and third screenshot is determined as an image binary classification dataset, and this image binary classification dataset is divided into a training set, a validation set, and a test set according to a first partitioning ratio. In other embodiments, this image binary classification dataset can also be divided into a training set and a test set according to a second partitioning ratio. Further, the preset binary classification neural network is trained using the partitioned training set, validation set, and test set to obtain the final binary classification network and store it in the database. The binary classification neural network can be a convolutional neural network; in other embodiments, a recurrent neural network can also be used for binary classification. It should be noted that the second railway signal cable route map includes several different cable routes.

[0044] S202: Preprocess the second railway signal cable route map and the target equipment location mask map to obtain the target input data.

[0045] Specifically, after determining the target equipment location mask image corresponding to the abnormal railway signaling equipment, both the second railway signaling cable path image and the target equipment location mask image are preprocessed to make the input data more consistent with the model's input requirements. The specific preprocessing process is as follows: the second railway signaling cable path image is converted to an image format and its size is adjusted to a second preset size to obtain the first target input data. This size adjustment can be performed using the `cv2.resize` function in the OpenCV library; in other embodiments, it can also be performed using the `transforms.Resize` function in PyTorch. Similarly, the size of the target equipment location mask image is adjusted to a second preset size to obtain the second target input data. The second preset size can be (1024, 1024) or (512, 512).

[0046] Finally, the first target input data and the second target input data are concatenated to obtain the target input data. For details, please refer to step S104, which will not be repeated here.

[0047] S203: Input the target input data into the cable path diagram analysis model to obtain the target associated cable path diagram corresponding to the abnormal railway signal equipment.

[0048] S204: Overlay the target associated cable route map onto the second railway signal cable route map and highlight it.

[0049] Specifically, the target input data is input into the cable path diagram analysis model to obtain the cable path diagram of the railway signaling equipment that needs to be troubleshooted, improving the efficiency of fault diagnosis and avoiding the time-consuming process of personnel identifying the cable path diagram that needs troubleshooting. Furthermore, the target-related cable path diagram is finally overlaid on the second railway signaling cable path diagram and highlighted, providing a reference for subsequent maintenance personnel to troubleshoot the fault.

[0050] In other embodiments, historical anomalies of railway signaling equipment that have experienced abnormalities are obtained from the historical investigation records of cable routes. The first occurrence frequency of each historical anomaly is counted. The more occurrence frequencies, the more likely the railway signaling equipment is to experience the corresponding historical anomaly. Then, in descending order of the first occurrence frequency, the historical anomalies with the highest occurrence frequency are selected and identified as likely anomalies, i.e., anomalies that are likely to occur in the railway signaling equipment. Further, from the historical investigation records of cable routes, the abnormal environmental factors of the corresponding historical associated cable route diagrams are obtained when a single likely anomaly occurs in the historical railway signaling equipment. That is, the abnormal environment of the cable corresponding to the faulty associated cable route diagram, such as high temperature, high pressure, etc. The second occurrence frequency of each abnormal environmental factor is counted. The more occurrence frequencies, the more likely the cable in the corresponding historical associated route diagram is to have the corresponding abnormal environmental factor. Further, in descending order of the second occurrence frequency, the second-highest abnormal environmental factor is selected and identified as the easily induced abnormal factor corresponding to this single likely anomaly. That is, the abnormal environmental factors in the associated cable routes that are likely to induce the corresponding likely anomaly in the railway signaling equipment.

[0051] Furthermore, the first weight for each likely anomaly and the second weight for each corresponding likely anomaly-inducing factor are calculated. The first weight is the ratio of the first occurrence count of each likely anomaly to the sum of the first occurrence counts of all likely anomalies. The second weight is the ratio of the second occurrence count of a single likely anomaly-inducing factor corresponding to the likely anomaly to the sum of the second occurrence counts of all corresponding likely anomaly-inducing factors. Further, when the target anomaly of the abnormal railway signaling equipment is a likely anomaly, the weighted product of the first weight of the target anomaly and the second weights of each likely anomaly-inducing factor in the abnormal environmental factors of the target associated cable path diagram is calculated. The larger the weighted product, the greater the probability that the target anomaly is caused by the corresponding likely anomaly-inducing factor. Finally, the weighted products are summed to obtain the weighted product sum. The larger the weighted product sum, the greater the likelihood that the target anomaly is caused by the likely anomaly-inducing factor in the abnormal environmental factors of the target associated cable path diagram. The weighted product is compared with a preset product sum threshold. If the weighted product sum is greater than the product sum threshold, it indicates that the target anomaly is likely caused by an easily induced anomaly factor in the abnormal environmental factors of the target associated cable path diagram. This means that the target cable path in the target associated cable path diagram is indeed the cable path that needs to be investigated. Therefore, the target associated cable path diagram is verified as passed. By investigating the target cable path in this diagram, the fault point can be found with a high probability, improving the efficiency of the investigation. Finally, the maintenance personnel investigate the target cable path corresponding to the target associated cable path diagram. It should be noted that the abnormal environmental factors of the target associated cable path diagram are determined by: acquiring the corresponding image information through cameras on the cable path corresponding to the target associated cable path diagram, identifying the abnormal environmental factors, and sending the information to the server via a terminal.

[0052] In another embodiment, the target cable path corresponding to the target associated cable path map is investigated. One feasible implementation is as follows: Cables containing factors prone to causing anomalies within the target cable path are identified as target cable segments. Then, based on weighted products, the investigation priority of the corresponding target cable segments is determined. The larger the weighted product, the greater the probability that the corresponding factor causing anomalies will lead to target anomalies, and the higher the investigation priority of the corresponding target cable segment. Specifically, a preset priority matching table can be used to match the investigation priority corresponding to each weighted product. The priority matching table includes different weighted product ranges and their corresponding investigation priorities. The investigation priority ranges from 1 to 10. For example, the weighted product range corresponding to investigation priority 10 is a1 to a2. If the weighted product A is within this a1 to a2 range, it means that the highest investigation priority of the corresponding target cable segment is 10. Finally, according to each investigation priority, the target cable segments in the target cable path are investigated sequentially, thereby further improving the efficiency of troubleshooting faults causing target anomalies.

[0053] The implementation principle of the cable path diagram analytical model training method in this application embodiment is as follows: A first screenshot containing railway signal equipment is extracted from the first railway signal cable path diagram, and then the corresponding railway signal equipment location mask is determined, thereby representing the location information of the railway signal equipment in the corresponding first railway signal cable path diagram. Further, the railway signal equipment location mask corresponding to a single first screenshot, the first railway signal cable path diagram, and the associated cable path diagram are used as training data to train the image segmentation network. This allows the network to continuously learn and acquire the ability to segment the associated cable path diagram corresponding to the railway signal equipment from the first railway signal cable path diagram, ultimately obtaining the cable path diagram analytical model. Once a railway signal equipment malfunctions, simply inputting the location mask of the malfunctioning railway signal equipment and the corresponding railway signal cable path diagram into this cable path diagram analytical model quickly determines the cable path that needs to be investigated, improving fault diagnosis efficiency.

[0054] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0055] Please see Figure 3 This is a schematic diagram of the structure of the analytical model training device for cable path maps provided in this application embodiment. This analytical model training device for cable path maps can be implemented as all or part of a device through software, hardware, or a combination of both. The device includes an information acquisition module 11, a mask determination module 12, a path determination module 13, and a model training module 14.

[0056] Information acquisition module 11 is used to acquire at least one first railway signal cable route map, the first railway signal cable route map including different railway signal devices that are connected to each other; The mask determination module 12 is used to extract at least one first screenshot containing railway signal equipment from each of the first railway signal cable route maps, and generate a corresponding railway signal equipment location mask map based on the first screenshot. The path determination module 13 is used to determine the associated cable path diagram of the railway signal equipment in each first screenshot in the corresponding first railway signal cable path diagram. The associated cable path diagram is the part of the cable path diagram that is most associated with the corresponding railway signal equipment when an anomaly occurs. The model training module 14 is used to train a preset image segmentation network based on the railway signal equipment location mask map, associated cable path map and the first railway signal cable path map corresponding to each first screenshot, so as to obtain a cable path map parsing model. The cable path map parsing model is a model that outputs the associated cable path map of the corresponding railway signal equipment based on the input railway signal cable path map and railway signal equipment location mask map.

[0057] Optional, model training module 14, specifically used for: Convert the first railway signal cable route map corresponding to each first screenshot into an input cable route map in image format, and adjust the size of the input cable route map to a first preset size to obtain the corresponding first input data; Adjust the size of the railway signal equipment location mask image corresponding to each first screenshot to the first preset size to obtain the corresponding second input data; The first and second input data corresponding to the same first screenshot are concatenated to obtain the final input data. Based on the final input data and the associated cable path map corresponding to each first screenshot, the preset image segmentation network is trained.

[0058] It should be noted that the cable path diagram analytical model training device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the cable path diagram analytical model training method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the cable path diagram analytical model training device and the cable path diagram analytical model training method embodiment provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiment, which will not be repeated here.

[0059] Please see Figure 4 This is a schematic diagram of the cable path map parsing device provided in an embodiment of this application. This cable path map parsing device can be implemented as all or part of a device through software, hardware, or a combination of both. The device includes a data acquisition module 21, an image processing module 22, a model prediction module 23, and a path overlay module 24.

[0060] The data acquisition module 21 is used to acquire a second railway signal cable path map containing abnormal railway signal equipment, a cable path map analytical model obtained by training the analytical model of the cable path map in any of the above embodiments, and to acquire a target equipment location mask map corresponding to the abnormal railway signal equipment.

[0061] Image processing module 22 is used to preprocess the second railway signal cable route map and the target equipment location mask map to obtain target input data.

[0062] The model prediction module 23 is used to input the target input data into the cable path map analysis model to obtain the target associated cable path map corresponding to the abnormal railway signal equipment.

[0063] The path overlay module 24 is used to overlay the target associated cable path map onto the second railway signal cable path map and highlight it.

[0064] Optionally, the image processing module 22 is specifically used for: The second railway signal cable route map is converted into an image format and its size is adjusted to the second preset size to obtain the first target input data; The size of the target device location mask is adjusted to the second preset size to obtain the second target input data. The first target input data and the second target input data are then concatenated to obtain the target input data.

[0065] Optional, such as Figure 5 As shown, the device also includes a path verification module 25, specifically used for: Obtain historical anomalies of railway signaling equipment that have experienced anomalies, count the first occurrence count of each historical anomaly, and select the historical anomaly with the highest first occurrence count from all historical anomalies to identify those that are prone to occur. Obtain the abnormal environment factors of the historical associated cable path map corresponding to the single abnormality of the historical railway signal equipment, and count the second occurrence of each abnormal environment factor. The abnormal environment factor is the abnormal environment of the cable corresponding to the associated cable path map of the identified fault. According to the order of the second occurrence frequency from large to small, select the second number of abnormal environmental factors from each abnormal environmental factor and determine them as the corresponding easily induced abnormal factors that are prone to abnormality. Calculate the first weight of each prone anomaly and the second weight of each corresponding prone anomaly inducing factor. The first weight is the ratio of the first occurrence count of each prone anomaly to the sum of the first occurrence counts of all prone anomalies. The second weight is the ratio of the second occurrence count of a single prone anomaly inducing factor corresponding to a prone anomaly to the sum of the second occurrence counts of all corresponding prone anomaly inducing factors. When the target anomaly of the abnormal railway signaling equipment is a likely anomaly, the target associated cable path map is verified based on the first weight of the target anomaly and the second weight of the easily induced anomaly factor in the abnormal environmental factors of the target associated cable path map.

[0066] Optional, the route verification module 25 is specifically used for: Calculate the first weight of the target anomaly and the second weight of each easily induced anomaly factor in the anomaly environmental factors of the target-related cable path map, and obtain the corresponding weight product; The weights are multiplied and summed to obtain the weight product sum, which is then compared with a preset product sum threshold. If the sum of the weights is greater than the product sum threshold, the verification of the target associated cable path map is deemed successful, and the target cable path corresponding to the target associated cable path map is investigated.

[0067] Optional, the route verification module 25 is specifically used for: Determine at least one target cable segment from the target cable path corresponding to the target associated cable path map. The target cable segment is a part of the target cable path that contains factors that are prone to inducing anomalies. The priority of the investigation of the corresponding target cable segment is determined by the weight product. The larger the weight product, the higher the priority of the investigation of the corresponding target cable segment. The target cable segments in the target cable path are investigated sequentially according to the investigation priority from high to low.

[0068] This application also discloses a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it employs a cable routing diagram analytical model training method and an analytical method as described in the above embodiments.

[0069] The computer program can be stored in a computer-readable medium. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or certain middleware. The computer-readable medium includes any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the computer-readable medium includes, but is not limited to, the above-mentioned components.

[0070] The above-described cable routing diagram analytical model training method and analytical method are stored in the computer-readable storage medium and loaded and executed on the processor to facilitate the storage and application of the above method.

[0071] This application also discloses an electronic device in which a computer program is stored in a computer-readable storage medium. When the computer program is loaded and executed by a processor, it employs the above-mentioned analytical model training method and analytical method for cable routing diagrams.

[0072] The electronic device can be a desktop computer, a laptop computer, or a cloud server, and includes, but is not limited to, a processor and a memory. For example, the electronic device may also include input / output devices, network access devices, and buses.

[0073] The processor can be a central processing unit (CPU). Of course, depending on the actual use, it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it.

[0074] The memory can be an internal storage unit of an electronic device, such as a hard disk or RAM, or an external storage device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD), or flash memory card (FC) equipped on the electronic device. Furthermore, the memory can be a combination of an internal storage unit and an external storage device. The memory is used to store computer programs and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or will be output. This application does not limit this.

[0075] In this electronic device, the cable routing diagram analytical model training method and analytical method of the above embodiment are stored in the memory of the electronic device and loaded and executed on the processor of the electronic device for convenient use.

[0076] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for analyzing cable routing diagrams, characterized in that, The method includes: Obtain a second railway signal cable route map containing abnormal railway signal equipment, obtain an analytical model of the cable route map using the analytical model training method of the cable route map, and obtain a target equipment location mask map corresponding to the abnormal railway signal equipment; The second railway signal cable route map and the target equipment location mask map are preprocessed to obtain the target input data; The target input data is input into the cable path map analysis model to obtain the target associated cable path map corresponding to the abnormal railway signal equipment; The target associated cable path map is overlaid on the second railway signal cable path map and highlighted; wherein, historical anomalies of railway signal equipment that have experienced anomalies are obtained, the first occurrence count of each historical anomaly is counted, and the historical anomaly with the highest first occurrence count is selected from the historical anomalies in descending order of the first occurrence count to determine it as a likely anomaly; Obtain the abnormal environment factors of the historical associated cable path map corresponding to the occurrence of a single abnormality in the historical railway signal equipment, and count the second occurrence number of each of the abnormal environment factors. The abnormal environment factor is the abnormal environment of the cable corresponding to the associated cable path map of the identified fault. According to the order of the second occurrence frequency from largest to smallest, select the second number of abnormal environmental factors from each of the abnormal environmental factors and determine them as the corresponding easily induced abnormal factors that are prone to abnormality. Calculate the first weight of each of the easily occurring anomalies and the second weight of each corresponding easily induced anomaly factor. The first weight is the ratio of the first occurrence number of each easily occurring anomaly to the sum of the first occurrence numbers of all easily occurring anomalies. The second weight is the ratio of the second occurrence number of a single easily induced anomaly factor corresponding to the easily occurring anomaly to the sum of the second occurrence numbers of all corresponding easily induced anomaly factors. When the target anomaly of the abnormal railway signaling equipment is the easily occurring anomaly, the target associated cable path map is verified based on the first weight of the target anomaly and the second weight of the easily induced anomaly factor in the abnormal environmental factors of the target associated cable path map.

2. The method for analyzing cable routing diagrams according to claim 1, characterized in that, The process of obtaining the target equipment location mask image corresponding to the abnormal railway signaling equipment specifically includes: Obtain at least one third railway signal cable route map, and extract at least one second screenshot that does not contain railway signal equipment and one third screenshot that contains railway signal equipment from each of the third railway signal cable route maps; Each of the second screenshots and each of the third screenshots are determined as an image binary classification dataset, and a preset binary classification neural network is trained using the image binary classification dataset to obtain the final binary classification network after training and store it in a preset database. The final binary classification network can determine whether the input screenshot contains railway signal equipment. An initial screenshot corresponding to the abnormal railway signal equipment is extracted from the second railway signal cable path map, and the initial screenshot is input into the final binary classification network to obtain the corresponding output result; Based on the output results, determine whether the corresponding initial screenshot contains railway signal equipment. If so, generate a target equipment location mask image corresponding to the abnormal railway signal equipment based on the initial screenshot. If not, repeat the step of extracting the initial screenshot corresponding to the abnormal railway signaling equipment from the second railway signaling cable route map.

3. The method for analyzing cable routing diagrams according to claim 1, characterized in that, The step of preprocessing the second railway signal cable route map and the target equipment location mask map to obtain target input data specifically includes: The second railway signal cable route map is converted into an image format and its size is adjusted to a second preset size to obtain the first target input data; The size of the target device location mask is adjusted to the second preset size to obtain the second target input data. The first target input data and the second target input data are then concatenated to obtain the target input data.

4. The method for analyzing cable routing diagrams according to claim 1, characterized in that, The verification of the target associated cable path map based on the first weight of the target anomaly and the second weight of each easily induced anomaly factor in the anomaly environmental factors of the target associated cable path map specifically includes: Calculate the first weight of the target anomaly and the second weight of each easily induced anomaly factor in the abnormal environmental factors of the target associated cable path map to obtain the corresponding weight product; The weights are multiplied together to obtain a weight product sum, and the weight product sum is compared with a preset product sum threshold. If the sum of the weighted products is greater than the product sum threshold, then the verification of the target associated cable path map is determined to be successful, and the target cable path corresponding to the target associated cable path map is investigated.

5. The method for analyzing cable routing diagrams according to claim 4, characterized in that, The step of investigating the target cable paths corresponding to the target associated cable path map specifically includes: At least one target cable segment is determined from the target cable path corresponding to the target associated cable path map. The target cable segment is a part of the cable in the target cable path that contains factors that are prone to induce abnormalities. The investigation priority of the corresponding target cable segment is determined based on the weighted product. The larger the weighted product, the higher the investigation priority of the corresponding target cable segment. The target cable segments in the target cable path are investigated sequentially according to the investigation priority from high to low.

6. The method for analyzing cable routing diagrams according to claim 1, characterized in that, The analytical model training method for the cable path diagram includes: Obtain at least one first railway signal cable route map, the first railway signal cable route map including different railway signal devices that are connected to each other; Take at least one first screenshot containing railway signal equipment from each of the first railway signal cable route maps, and generate a corresponding railway signal equipment location mask map based on the first screenshot; Determine the associated cable path diagram of each railway signaling device in the first screenshot in the corresponding first railway signaling cable path diagram. The associated cable path diagram is the part of the cable path diagram that is most associated with the corresponding railway signaling device when an anomaly occurs. Based on the railway signal equipment location mask map, associated cable path map, and first railway signal cable path map corresponding to each of the first screenshots, a preset image segmentation network is trained to obtain a cable path map parsing model. The cable path map parsing model is a model that outputs the associated cable path map of the corresponding railway signal equipment based on the input railway signal cable path map and railway signal equipment location mask map.

7. The method for analyzing cable routing diagrams according to claim 6, characterized in that, The step of training a preset image segmentation network based on the railway signal equipment location mask map, associated cable path map, and first railway signal cable path map corresponding to each of the first screenshots specifically includes: The first railway signal cable route map corresponding to each of the first screenshots is converted into an input cable route map in image format, and the size of the input cable route map is adjusted to a first preset size to obtain the corresponding first input data; Adjust the size of the railway signal equipment location mask image corresponding to each of the first screenshots to the first preset size to obtain the corresponding second input data; The first input data and the second input data corresponding to the same first screenshot are concatenated to obtain the final input data. Based on the final input data and the associated cable path map corresponding to each of the first screenshots, the preset image segmentation network is trained.

8. A training apparatus for an analytical model of a cable path diagram, used to implement the analytical model training method for a cable path diagram as described in claim 6, characterized in that, include: The information acquisition module (11) is used to acquire at least one first railway signal cable route map, the first railway signal cable route map including different railway signal devices that are connected to each other; The mask determination module (12) is used to extract at least one first screenshot containing railway signal equipment from each of the first railway signal cable route maps, and generate a corresponding railway signal equipment location mask map based on the first screenshot. The path determination module (13) is used to determine the associated cable path diagram of each railway signal device in the first screenshot in the corresponding first railway signal cable path diagram. The associated cable path diagram is the part of the cable path diagram that is most associated with the corresponding railway signal device when an anomaly occurs. The model training module (14) is used to train a preset image segmentation network based on the railway signal equipment location mask map, associated cable path map and first railway signal cable path map corresponding to each of the first screenshots, to obtain a cable path map parsing model. The cable path map parsing model is a model that outputs the associated cable path map of the corresponding railway signal equipment based on the input railway signal cable path map and railway signal equipment location mask map.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it employs the method described in any one of claims 1-7.

Images