Auxiliary retrieval method and system applied to railway signal centralized monitoring system

Abstract

According to the auxiliary retrieval method and system applied to the railway signal centralized monitoring system, the identity information of the user is recognized, whether the user has the retrieval permission or not is judged, and the data retrieval safety is guaranteed; a user triggers a retrieval demand, related data features and related data parameters are obtained based on the retrieval demand, multiple visual chart models are automatically matched for the user based on the related data features, an optimal chart model is determined based on the multiple visual chart models, and retrieval information is rapidly and visually displayed. Marking the related data parameters in the optimal chart model to obtain an optimal visual chart, judging whether abnormal data parameters exist in the related data parameters or not, highlighting the abnormal data parameters on the optimal visual chart, generating an abnormal data visual chart, and assisting a user to quickly analyze abnormal data; and performing machine learning on the abnormal data parameters, positioning a fault point, analyzing a fault reason, generating a fault prediction tree taking the fault point as a center, and assisting a user in finding potential anomalies.

Description

Technical Field

[0001] The present invention relates to the technical field of railway signal centralized monitoring, and in particular to an auxiliary reading method and system applied to a railway signal centralized monitoring system. Background Art

[0002] The existing railway signal centralized monitoring system (hereinafter referred to as the "monitoring system") is an important equipment for ensuring railway traffic safety. The system performs real-time status monitoring, data recording, statistical analysis and fault alarm for basic railway signal equipment (such as switches, signal machines, track circuits, etc.) and transportation control systems (such as CTC, interlocking, train control, etc.).

[0003] With the development of monitoring systems, monitoring data is becoming increasingly voluminous, necessitating the use of assisted access functions to enable electrical maintenance personnel to efficiently access, analyze, and process signal equipment monitoring data. The efficiency of assisted access in monitoring systems directly impacts the effectiveness of troubleshooting and maintenance work. However, when accessing large amounts of data, the existing assisted access function, which involves manually entering query criteria, is not only inefficient but also offers unintuitive data display, hindering troubleshooting efficiency.

[0004] Therefore, it is necessary to improve the auxiliary reading function of the monitoring system to solve the above problems. Summary of the Invention

[0005] In view of the above-mentioned problem that when the amount of data to be retrieved is large, the manual input of query conditions in the existing auxiliary retrieval function is not only inefficient, but the data display is also not intuitive, which affects the efficiency of troubleshooting, one of the purposes of this application is to provide an auxiliary retrieval method and system applied to the railway signal centralized monitoring system, which improves the retrieval efficiency and data intuitiveness by changing the data retrieval method and automatically matching visual charts according to user retrieval needs.

[0006] To achieve the above objectives, this application adopts the following technical solutions: The auxiliary reading method applied to the railway signal centralized monitoring system comprises the following steps: Step S10: Identify user identity information and determine whether the user has access permission; if so, trigger access request, and obtain relevant data features and relevant data parameters based on the access request; Step S20: automatically matching multiple visual chart models for the user based on the relevant data features; and determining the best chart model based on the multiple visual chart models; Step S30: marking the relevant data parameters in the optimal chart model to obtain an optimal visualization chart; and determining whether there are abnormal data parameters in the relevant data parameters. If so, highlighting the abnormal data parameters on the optimal visualization chart and generating an abnormal data visualization chart; Step S40: Perform machine learning on the abnormal data parameters to locate the fault point and predict the cause of the abnormality; based on the fault cause, generate a fault prediction tree centered on the fault point.

[0007] In one embodiment disclosed in the present application, in step S10, user identity information is identified to determine whether the user has access permission; if so, a access request is triggered, and relevant data features and relevant data parameters are obtained based on the access request, including: Creating an identity information database, identifying and judging the user's identity information; if the user's identity information exists in the identity information database, then judging that the user has access rights; if the user's identity information does not exist in the identity information database, then judging that the user does not have access rights; If the user has access permission, the user inputs access information to trigger the access demand, and natural language processing technology is used to perform semantic recognition on the access information to obtain the relevant data features and relevant data parameters required by the user; wherein, the relevant data features include access type features, access field features and access intention features, and the relevant data parameters include power supply data parameters, track circuit data parameters, turnout data parameters, signal data parameters and signal equipment working environment parameters.

[0008] In one embodiment disclosed in the present application, in step S20, based on the relevant data features, multiple visual chart models are automatically matched for the user; and based on the multiple visual chart models, determining the optimal chart model includes: Collect railway industry standard charts and create a chart model database, wherein the railway industry standard charts include statistical charts, heat matrix charts, sunburst charts, and radar charts; based on the reference type characteristics, reference field characteristics, and reference intention characteristics, configure chart matching rules using a rule engine; match railway industry standard charts in the chart model database based on the chart matching rules to obtain a matching confidence; when the matching confidence exceeds a confidence threshold, determine that the corresponding railway industry standard chart is a visual chart model; The multiple visual chart models are displayed in descending order of the matching confidence, and the user selects the visual chart model that best meets his / her usage habits from the multiple visual chart models as the optimal chart model.

[0009] In one embodiment disclosed in the present application, in step S30, the relevant data parameters are marked in the optimal chart model to obtain an optimal visualization chart; and it is determined whether there are abnormal data parameters in the relevant data parameters. If so, the abnormal data parameters are highlighted on the optimal visualization chart, and generating the abnormal data visualization chart includes: Marking one or more of the power supply data parameters, track circuit data parameters, switch data parameters, signal data parameters, and signal equipment working environment parameters in the optimal chart model to obtain an optimal visualization chart; Parameter threshold ranges are preset for the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters respectively. When one or more of the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters exceed the parameter threshold ranges, it is determined that abnormal data parameters exist in the relevant data parameters, the abnormal data parameters are highlighted and / or animatedly flashing on the optimal visualization chart, and an abnormal data visualization chart is generated based on the abnormal data parameters.

[0010] In one embodiment disclosed in the present application, in step S40, machine learning is performed on the abnormal data parameters to locate the fault point and analyze the fault cause; and based on the fault cause, generating a fault prediction tree centered on the fault point includes: Collect a large amount of historical abnormal data parameters for machine learning to generate a fault analysis model, input the abnormal data parameters into the fault analysis model, locate the fault point and output the fault cause; Based on the fault cause, the fault path is derived through a Bayesian network or a decision tree to generate a fault prediction tree centered on the fault point.

[0011] The auxiliary reading system used in the railway signal centralized monitoring system includes the following modules: Identity recognition module, used to identify user identity information and determine whether the user has access permission; A demand triggering module is used to trigger a retrieval demand and obtain relevant data features and relevant data parameters based on the retrieval demand; A chart matching module, configured to automatically match a plurality of visual chart models for a user based on the relevant data features; a chart confirmation module, configured to determine an optimal chart model based on the multiple visual chart models; a chart visualization module, configured to mark the relevant data parameters in the optimal chart model to obtain an optimal visualization chart; and determine whether there are abnormal data parameters in the relevant data parameters. If so, highlight the abnormal data parameters on the optimal visualization chart and generate an abnormal data visualization chart; The potential fault prediction module is used to perform machine learning on the abnormal data parameters, locate the fault point and analyze the fault cause; based on the fault cause, generate a fault prediction tree centered on the fault point.

[0012] In one embodiment of the present disclosure, the identity recognition module is configured to recognize user identity information and determine whether the user has access rights, including: creating an identity information library, recognizing user identity information, determining whether the user has access rights if the user identity information exists in the identity information library, and determining that the user does not have access rights if the user identity information does not exist in the identity information library; The demand triggering module is configured to trigger access demand and obtain relevant data features and relevant data parameters based on the access demand, including: If the user has access rights, the user inputs access information to trigger access demand, and uses natural language processing technology to recognize the semantics of the access information to obtain relevant data features and relevant data parameters required by the user; wherein the relevant data features include access type features, access field features and access intent features, and the relevant data parameters include power supply data parameters, track circuit data parameters, switch machine data parameters, signal machine data parameters and signal equipment working environment parameters.

[0013] In one embodiment of the present disclosure, the chart matching module is configured to automatically match a plurality of visualization chart models for the user based on the relevant data features, including: Collecting railway industry standard charts, creating a chart model database, and the railway industry standard charts including statistical charts, heat matrix charts, sunrise charts and radar charts; based on the access type features, access field features and access intent features, using a rule engine to configure chart matching rules, matching railway industry standard charts in the chart model database based on the chart matching rules to obtain a matching confidence; when the matching confidence exceeds a confidence threshold, determining that the corresponding railway industry standard chart is a visualization chart model; The chart confirmation module is configured to determine the best chart model based on the plurality of visualization chart models, including: The plurality of visualization chart models are displayed in order from high to low according to the matching confidence, and the user selects a visualization chart model that best meets his or her usage habits from the plurality of visualization chart models as the best chart model.

[0014] In one embodiment of the present disclosure, the chart visualization module is configured to label the relevant data parameters in the best chart model to obtain the best visualization chart, and determine whether there are abnormal data parameters in the relevant data parameters, including: Marking one or more of the power supply data parameters, track circuit data parameters, switch data parameters, signal data parameters, and signal equipment working environment parameters in the optimal chart model to obtain an optimal visualization chart; Parameter threshold ranges are preset for the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters respectively. When one or more of the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters exceed the parameter threshold ranges, it is determined that abnormal data parameters exist in the relevant data parameters, the abnormal data parameters are highlighted and / or animatedly flashing on the optimal visualization chart, and an abnormal data visualization chart is generated based on the abnormal data parameters.

[0015] In one embodiment disclosed in the present application, the potential fault prediction module is configured to perform machine learning on the abnormal data parameters, locate the fault point, and analyze the fault cause; and based on the fault cause, generating a fault prediction tree centered on the fault point includes: Collect a large amount of historical abnormal data parameters for machine learning to generate a fault analysis model, input the abnormal data parameters into the fault analysis model, locate the fault point and output the fault cause; Based on the fault cause, the fault path is derived through a Bayesian network or a decision tree to generate a fault prediction tree centered on the fault point.

[0016] Compared with the prior art, the beneficial effects of the present invention are: identifying user identity information and judging whether the user has access authority to ensure the security of data access; the user triggers the access demand, and obtains relevant data features and relevant data parameters based on the access demand, and automatically matches multiple visual chart models for the user based on the relevant data features, and determines the best chart model based on the multiple visual chart models to display the access information in a fast and intuitive manner; marking the relevant data parameters in the best chart model to obtain the best visual chart, and judging whether there are abnormal data parameters in the relevant data parameters, if so, highlighting the abnormal data parameters on the best visual chart, and generating an abnormal data visual chart to assist users in quickly analyzing abnormal data; performing machine learning on the abnormal data parameters, locating the fault point and analyzing the fault cause, and generating a fault prediction tree centered on the fault point based on the fault cause, to assist users in discovering potential abnormalities, which is conducive to the efficient implementation of maintenance work. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A flowchart of the auxiliary access method for a railway signal centralized monitoring system provided in this application; Figure 2 This is a schematic diagram of the framework of the auxiliary reading system provided in this application for the railway signal centralized monitoring system. DETAILED DESCRIPTION

[0019] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are to be considered as illustrative in nature and not restrictive.

[0020] As used herein, the terms "comprise," "comprising," and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used in this specification are intended only to describe specific embodiments and are not intended to limit this application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0022] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0024] Figure 1This is a flow chart of the auxiliary access method applied to the railway signal centralized monitoring system provided by this application. The auxiliary access method applied to the railway signal centralized monitoring system includes the following steps: Step S10: Identify the user's identity information and determine whether the user has access rights; if so, trigger a access request, and obtain relevant data features and relevant data parameters based on the access request; Step S20: automatically matching multiple visual chart models for the user based on the relevant data features; and determining the best chart model based on the multiple visual chart models; Step S30: marking the relevant data parameters in the optimal chart model to obtain an optimal visualization chart; and determining whether there are abnormal data parameters in the relevant data parameters. If so, highlighting the abnormal data parameters on the optimal visualization chart and generating an abnormal data visualization chart; Step S40: Perform machine learning on the abnormal data parameters to locate the fault point and analyze the fault cause; based on the fault cause, generate a fault prediction tree centered on the fault point.

[0025] The auxiliary access method applied to the railway signal centralized monitoring system identifies user identity information and determines whether the user has access authority to ensure the security of data access; the user triggers the access demand, obtains relevant data features and relevant data parameters based on the access demand, automatically matches multiple visual chart models for the user based on the relevant data features, and determines the optimal chart model based on the multiple visual chart models to display the access information in a fast and intuitive manner; the relevant data parameters are marked in the optimal chart model to obtain the optimal visual chart, and it is determined whether there are abnormal data parameters in the relevant data parameters. If so, the abnormal data parameters are highlighted on the optimal visual chart, and an abnormal data visual chart is generated to assist the user in quickly analyzing the abnormal data; machine learning is performed on the abnormal data parameters to locate the fault point and analyze the fault cause. Based on the fault cause, a fault prediction tree centered on the fault point is generated to assist the user in discovering potential abnormalities, which is conducive to the efficient implementation of maintenance work.

[0026] Preferably, in step S10, the user identity information is identified to determine whether the user has access authority; if so, a access request is triggered, and relevant data features and relevant data parameters are obtained based on the access request, including: Create an identity information database and identify and judge the user's identity information. If the user's identity information exists in the identity information database, it is determined that the user has access rights. If the user's identity information does not exist in the identity information database, it is determined that the user does not have access rights. If the user has access permission, the user inputs access information to trigger the access demand, and natural language processing technology is used to perform semantic recognition on the access information to obtain the relevant data features and relevant data parameters required by the user; wherein, the relevant data features include access type features, access field features and access intention features, and the relevant data parameters include power supply data parameters, track circuit data parameters, turnout data parameters, signal data parameters and signal equipment working environment parameters.

[0027] In the above technical solution, the user registers an account and stores the registered account in the identity information database, so as to use the identity information database to identify and judge the user's identity information, thereby ensuring the security of railway signal data access. Users with access permissions input access information to trigger access requirements. The access information can be natural language (such as "check the abnormal current record of switch No. 12 yesterday"). Natural language processing technology is used to perform semantic recognition on the access information to obtain the relevant data features and relevant data parameters required by the user; the relevant data features include access type features, access field features and access intention features, among which the access type feature is the data type that the user wants to access (such as floating point type, Boolean type, when the user accesses the working status of the signal equipment, it is to access Boolean data), the access field feature is the signal equipment that the user wants to access (such as switch machine, signal machine), and the access intention feature is the purpose of the user's access (such as data trend, status distribution, data statistics), so that The user's access needs are characterized and decomposed to accurately identify the user's access needs; the relevant data parameters include but are not limited to the power supply data parameters, track circuit data parameters, turnout and switch machine data parameters, signal machine data parameters and signal equipment working environment parameters that the user wants to access, wherein the power supply data parameters include but are not limited to input current, output current, input voltage, output voltage, track circuit data parameters include but are not limited to track surface voltage / current, resistance and capacitance, turnout and switch machine data parameters include but are not limited to conversion force and turnout and switch machine working voltage, signal machine data parameters include but are not limited to light source type, light intensity, beam angle and signal machine working voltage, signal equipment working environment parameters include but are not limited to working temperature, humidity, seismic performance and protection level.

[0028] Preferably, in step S20, based on the relevant data features, a plurality of visual chart models are automatically matched for the user; and based on the plurality of visual chart models, determining the best chart model includes: Collect railway industry standard charts and create a chart model database. The railway industry standard charts include statistical charts, heat matrix charts, sunburst charts, and radar charts. Based on the query type characteristics, query field characteristics, and query intent characteristics, a rule engine is used to configure chart matching rules. Based on the chart matching rules, railway industry standard charts are matched in the chart model database to obtain a matching confidence level. When the matching confidence level exceeds a confidence threshold, the corresponding railway industry standard chart is determined to be a visualization chart model. The multiple visual chart models are displayed in descending order of the matching confidence, and the user selects the visual chart model that best meets his / her usage habits from the multiple visual chart models as the best chart model.

[0029] In the above technical solution, historical railway industry standard charts are collected and a chart model database is created. The chart models in the chart model database are all standard chart models used in the railway industry, ensuring the comprehensiveness and standardization of the chart models. The railway industry standard charts include statistical charts, heat matrix charts, sunburst charts, and radar charts. Statistical charts include, but are not limited to, percentage charts, line charts, bar charts, and scatter plots, and are used to visually display, including but not limited to, data development trends, data comparisons, and proportions. Heat matrix charts use color changes to represent the intensity or density of data and are used to visually display, including but not limited to, the status distribution of signal equipment. Sunburst charts use multiple concentric rings to represent different levels of data, with each ring representing a level, extending from the center to the outer layers, and are used to visually display, including but not limited to, signal equipment failure statistics. Radar charts are used to visually display, including but not limited to, comparing the health of signal equipment across the entire station. A rule engine is also used to configure chart matching rules. Based on these chart matching rules, railway industry standard charts are matched against the chart model database to obtain a match confidence level. When the match confidence level exceeds a confidence threshold, the corresponding railway industry standard chart is determined to be a visual chart model, thereby ensuring the accuracy of the chart model match. Railway industry standard charts with matching confidence exceeding a confidence threshold in a chart model database are used as visualization chart models to obtain multiple visualization chart models. Users select the visualization chart model that best suits their usage habits from the multiple visualization chart models as the best chart model, thereby ensuring that data can be displayed intuitively while making the chart conform to the user's usage habits, thereby ensuring the practicality of chart matching.

[0030] Preferably, in step S30, the relevant data parameters are marked in the optimal chart model to obtain an optimal visualization chart; and whether there are abnormal data parameters in the relevant data parameters is determined, and if so, the abnormal data parameters are highlighted on the optimal visualization chart, and generating the abnormal data visualization chart includes: Marking one or more of the power supply data parameters, track circuit data parameters, switch data parameters, signal data parameters, and signal equipment working environment parameters in the optimal chart model to obtain an optimal visualization chart; Parameter threshold ranges are preset for the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters respectively. When one or more of the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters exceed the parameter threshold ranges, it is determined that there are abnormal data parameters in the relevant data parameters, the abnormal data parameters are highlighted and / or animatedly flashing on the optimal visualization chart, and an abnormal data visualization chart is generated based on the abnormal data parameters.

[0031] In the above technical solution, when a user accesses one or more of the power supply data parameters, track circuit data parameters, turnout data parameters, signal data parameters, and signal equipment working environment parameters, the data parameters accessed by the user are marked in the optimal chart model to obtain the optimal visualization chart, thereby visually displaying the data parameters accessed by the user in a fast and intuitive manner, which is convenient for the user to quickly view. A parameter threshold range is preset for each of the above data parameters. When a data parameter exceeds the corresponding parameter threshold range, it is determined that there is an abnormal data parameter in the data parameter; the abnormal data parameter is highlighted and / or animated on the optimal visualization chart to provide a clear reminder to the user, so that the user can discover the abnormality in time and take measures to solve it; an abnormal data visualization chart is also generated based on the abnormal data parameter to assist the user in quickly analyzing the abnormal data. The abnormal data visualization chart includes but is not limited to a development trend chart of the abnormal data parameter and a signal equipment distribution chart associated with the abnormal data parameter.

[0032] Preferably, in step S40, machine learning is performed on the abnormal data parameters to locate the fault point and analyze the fault cause; based on the fault cause, generating a fault prediction tree centered on the fault point includes: Collect a large amount of historical abnormal data parameters for machine learning to generate a fault analysis model. Input the abnormal data parameters into the fault analysis model to locate the fault point and output the fault cause. Based on the fault cause, the fault path is deduced through a Bayesian network or decision tree to generate a fault prediction tree centered on the fault point.

[0033] In the above technical solution, a large amount of historical abnormal data parameters is collected to train a classification model (such as a random forest) to generate a fault analysis model. These abnormal data parameters are then fed into the fault analysis model to locate the fault point and output the fault cause. This helps users quickly identify the fault point and cause, thereby improving maintenance efficiency. Based on the fault cause, the fault path is derived using a Bayesian network or decision tree, generating a fault prediction tree centered on the fault point. Specifically, the fault prediction tree is formed with the faulty signaling device as the center, the fault path as the branches, and other signaling devices associated with the fault point as the nodes. This helps users identify potential anomalies and facilitates efficient maintenance.

[0034] Figure 2 This is a schematic diagram of the framework of the auxiliary reading system for the railway signal centralized monitoring system provided in this application. The auxiliary reading system for the railway signal centralized monitoring system includes the following modules: Identity recognition module, used to identify user identity information and determine whether the user has access permission; A demand triggering module is used to trigger a retrieval demand and obtain relevant data features and relevant data parameters based on the retrieval demand; A chart matching module is used to automatically match multiple visual chart models for users based on the relevant data features; A chart confirmation module, configured to determine an optimal chart model based on the multiple visual chart models; a chart visualization module, configured to mark the relevant data parameters in the optimal chart model to obtain an optimal visualization chart; and determine whether there are abnormal data parameters in the relevant data parameters. If so, highlight the abnormal data parameters on the optimal visualization chart and generate an abnormal data visualization chart; The potential fault prediction module is used to perform machine learning on the abnormal data parameters, locate the fault point and predict the cause of the abnormality; based on the cause of the abnormality, a fault prediction tree centered on the fault point is generated.

[0035] The auxiliary access system applied to the railway signal centralized monitoring system identifies user identity information and determines whether the user has access authority to ensure the security of data access; the user triggers the access demand, obtains relevant data features and relevant data parameters based on the access demand, and automatically matches multiple visual chart models for the user based on the relevant data features. Based on the multiple visual chart models, the optimal chart model is determined to display the access information in a fast and intuitive manner; the relevant data parameters are marked in the optimal chart model to obtain the optimal visual chart, and it is determined whether there are abnormal data parameters in the relevant data parameters. If so, the abnormal data parameters are highlighted on the optimal visual chart, and an abnormal data visual chart is generated to assist the user in quickly analyzing the abnormal data; machine learning is performed on the abnormal data parameters to locate the fault point and analyze the fault cause. Based on the fault cause, a fault prediction tree centered on the fault point is generated to assist the user in discovering potential abnormalities, which is conducive to the efficient implementation of maintenance work.

[0036] Preferably, the identity recognition module is used to identify the user's identity information and determine whether the user has access permission, including: Create an identity information database and identify and judge the user's identity information. If the user's identity information exists in the identity information database, it is determined that the user has access rights. If the user's identity information does not exist in the identity information database, it is determined that the user does not have access rights. The demand triggering module is used to trigger the access demand, and obtains relevant data features and relevant data parameters based on the access demand, including: If the user has access permission, the user inputs access information to trigger the access demand, and natural language processing technology is used to perform semantic recognition on the access information to obtain the relevant data features and relevant data parameters required by the user; wherein, the relevant data features include access type features, access field features and access intention features, and the relevant data parameters include power supply data parameters, track circuit data parameters, turnout data parameters, signal data parameters and signal equipment working environment parameters.

[0037] In the above technical solution, the user registers an account and stores the registered account in the identity information database, so as to use the identity information database to identify and judge the user's identity information, thereby ensuring the security of railway signal data access. Users with access permissions input access information to trigger access requirements. The access information can be natural language (such as "check the abnormal current record of switch No. 12 yesterday"). Natural language processing technology is used to perform semantic recognition on the access information to obtain the relevant data features and relevant data parameters required by the user; the relevant data features include access type features, access field features and access intention features, among which the access type feature is the data type that the user wants to access (such as floating point type, Boolean type, when the user accesses the working status of the signal equipment, it is to access Boolean data), the access field feature is the signal equipment that the user wants to access (such as switch machine, signal machine), and the access intention feature is the purpose of the user's access (such as data trend, status distribution, data statistics), so that The user's access needs are characterized and decomposed to accurately identify the user's access needs; the relevant data parameters include but are not limited to the power supply data parameters, track circuit data parameters, turnout and switch machine data parameters, signal machine data parameters and signal equipment working environment parameters that the user wants to access, wherein the power supply data parameters include but are not limited to input current, output current, input voltage, output voltage, track circuit data parameters include but are not limited to track surface voltage / current, resistance and capacitance, turnout and switch machine data parameters include but are not limited to conversion force and turnout and switch machine working voltage, signal machine data parameters include but are not limited to light source type, light intensity, beam angle and signal machine working voltage, signal equipment working environment parameters include but are not limited to working temperature, humidity, seismic performance and protection level.

[0038] Preferably, the chart matching module is used to automatically match multiple visual chart models for the user based on the relevant data features, including: Collect railway industry standard charts and create a chart model database. The railway industry standard charts include statistical charts, heat matrix charts, sunburst charts, and radar charts. Based on the query type characteristics, query field characteristics, and query intent characteristics, a rule engine is used to configure chart matching rules. Based on the chart matching rules, railway industry standard charts are matched in the chart model database to obtain a matching confidence level. When the matching confidence level exceeds a confidence threshold, the corresponding railway industry standard chart is determined to be a visualization chart model. The chart confirmation module is configured to determine the best chart model based on the multiple visual chart models, including: The multiple visual chart models are displayed in descending order of the matching confidence, and the user selects the visual chart model that best meets his / her usage habits from the multiple visual chart models as the best chart model.

[0039] In the above technical solution, historical railway industry standard charts are collected and a chart model database is created. The chart models in the chart model database are all standard chart models used in the railway industry, ensuring the comprehensiveness and standardization of the chart models. The railway industry standard charts include statistical charts, heat matrix charts, sunburst charts, and radar charts. Statistical charts include, but are not limited to, percentage charts, line charts, bar charts, and scatter plots, and are used to visually display, including but not limited to, data development trends, data comparisons, and proportions. Heat matrix charts use color changes to represent the intensity or density of data and are used to visually display, including but not limited to, the status distribution of signal equipment. Sunburst charts use multiple concentric rings to represent different levels of data, with each ring representing a level, extending from the center to the outer layers, and are used to visually display, including but not limited to, signal equipment failure statistics. Radar charts are used to visually display, including but not limited to, comparing the health of signal equipment across the entire station. A rule engine is also used to configure chart matching rules. Based on these chart matching rules, railway industry standard charts are matched against the chart model database to obtain a match confidence level. When the match confidence level exceeds a confidence threshold, the corresponding railway industry standard chart is determined to be a visual chart model, thereby ensuring the accuracy of the chart model match. Railway industry standard charts with matching confidence exceeding a confidence threshold in a chart model database are used as visualization chart models to obtain multiple visualization chart models. Users select the visualization chart model that best suits their usage habits from the multiple visualization chart models as the best chart model, thereby ensuring that data can be displayed intuitively while making the chart conform to the user's usage habits, thereby ensuring the practicality of chart matching.

[0040] Preferably, the chart visualization module is configured to mark the relevant data parameters in the optimal chart model to obtain an optimal visualization chart; and determine whether there are abnormal data parameters in the relevant data parameters. If so, highlight the abnormal data parameters on the optimal visualization chart, and generate the abnormal data visualization chart, including: Marking one or more of the power supply data parameters, track circuit data parameters, switch data parameters, signal data parameters, and signal equipment working environment parameters in the optimal chart model to obtain an optimal visualization chart; Parameter threshold ranges are preset for the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters respectively. When one or more of the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters exceed the parameter threshold ranges, it is determined that there are abnormal data parameters in the relevant data parameters, the abnormal data parameters are highlighted and / or animatedly flashing on the optimal visualization chart, and an abnormal data visualization chart is generated based on the abnormal data parameters.

[0041] In the above technical solution, when a user accesses one or more of the power supply data parameters, track circuit data parameters, turnout data parameters, signal data parameters, and signal equipment working environment parameters, the data parameters accessed by the user are marked in the optimal chart model to obtain the optimal visualization chart, thereby visually displaying the data parameters accessed by the user in a fast and intuitive manner, which is convenient for the user to quickly view. A parameter threshold range is preset for each of the above data parameters. When a data parameter exceeds the corresponding parameter threshold range, it is determined that there is an abnormal data parameter in the data parameter; the abnormal data parameter is highlighted and / or animated on the optimal visualization chart to provide a clear reminder to the user, so that the user can discover the abnormality in time and take measures to solve it; an abnormal data visualization chart is also generated based on the abnormal data parameter to assist the user in quickly analyzing the abnormal data. The abnormal data visualization chart includes but is not limited to a development trend chart of the abnormal data parameter and a signal equipment distribution chart associated with the abnormal data parameter.

[0042] Preferably, the potential fault prediction module is configured to perform machine learning on the abnormal data parameters, locate the fault point, and analyze the fault cause; based on the fault cause, generating a fault prediction tree centered on the fault point includes: Collect a large amount of historical abnormal data parameters for machine learning to generate a fault analysis model. Input the abnormal data parameters into the fault analysis model to locate the fault point and output the fault cause. Based on the fault cause, the fault path is deduced through a Bayesian network or decision tree to generate a fault prediction tree centered on the fault point.

[0043] In the above technical solution, a large amount of historical abnormal data parameters is collected to train a classification model (such as a random forest) to generate a fault analysis model. These abnormal data parameters are then fed into the fault analysis model to locate the fault point and output the fault cause. This helps users quickly identify the fault point and cause, thereby improving maintenance efficiency. Based on the fault cause, the fault path is derived using a Bayesian network or decision tree, generating a fault prediction tree centered on the fault point. Specifically, the fault prediction tree is formed with the faulty signaling device as the center, the fault path as the branches, and other signaling devices associated with the fault point as the nodes. This helps users identify potential anomalies and facilitates efficient maintenance.

[0044] From the content of the above embodiment, the auxiliary browsing method and system applied to the railway signal centralized monitoring system identify user identity information, judge whether the user has browsing permission, so as to ensure the browsing security of data; the user triggers the browsing demand, obtains related data features and related data parameters based on the browsing demand, automatically matches a plurality of visualization chart models for the user based on the related data features, determines the best chart model based on the plurality of visualization chart models, and displays the browsing information in a fast and intuitive manner; the related data parameters are marked in the best chart model to obtain the best visualization chart, and it is judged whether there is an abnormal data parameter in the related data parameters; if yes, the abnormal data parameter is highlighted on the best visualization chart, and an abnormal data visualization chart is generated to assist the user in quickly analyzing the abnormal data; the machine learning is performed on the abnormal data parameter, the fault point is located and the fault reason is analyzed, the fault prediction tree centered on the fault point is generated based on the fault reason, the potential abnormality is found for the user, and the efficient maintenance work is facilitated.

[0045] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. An auxiliary reading method applied to a railway signal centralized monitoring system, characterized in that: It includes the following steps: Step S10: Identify user identity information and determine whether the user has access permission; if so, trigger access request, and obtain relevant data features and relevant data parameters based on the access request; Step S20: automatically matching multiple visual chart models for the user based on the relevant data features; and determining the best chart model based on the multiple visual chart models; Step S30: marking the relevant data parameters in the optimal chart model to obtain an optimal visualization chart; and determining whether there are abnormal data parameters in the relevant data parameters. If so, highlighting the abnormal data parameters on the optimal visualization chart and generating an abnormal data visualization chart; Step S40: Perform machine learning on the abnormal data parameters to locate the fault point and analyze the fault cause; based on the fault cause, generate a fault prediction tree centered on the fault point.

2. The auxiliary access method applied to the railway signal centralized monitoring system according to claim 1 is characterized in that: In step S10, the user's identity information is identified to determine whether the user has access authority; If so, a retrieval request is triggered, and relevant data features and relevant data parameters are obtained based on the retrieval request, including: Creating an identity information database, identifying and judging the user's identity information; if the user's identity information exists in the identity information database, then judging that the user has access rights; if the user's identity information does not exist in the identity information database, then judging that the user does not have access rights; If the user has access permission, the user inputs access information to trigger the access demand, and natural language processing technology is used to perform semantic recognition on the access information to obtain the relevant data features and relevant data parameters required by the user; wherein, the relevant data features include access type features, access field features and access intention features, and the relevant data parameters include power supply data parameters, track circuit data parameters, turnout data parameters, signal data parameters and signal equipment working environment parameters.

3. The auxiliary access method applied to the railway signal centralized monitoring system according to claim 2 is characterized in that: In step S20, based on the relevant data features, automatically matching multiple visual chart models for the user; based on the multiple visual chart models, determining the best chart model includes: Collect railway industry standard charts and create a chart model database, wherein the railway industry standard charts include statistical charts, heat matrix charts, sunburst charts, and radar charts; based on the query type characteristics, query field characteristics, and query intention characteristics, configure chart matching rules using a rule engine; match railway industry standard charts in the chart model database based on the chart matching rules to obtain a matching confidence; when the matching confidence exceeds a confidence threshold, determine that the corresponding railway industry standard chart is a visual chart model; The multiple visual chart models are displayed in descending order of the matching confidence, and the user selects the visual chart model that best meets his / her usage habits from the multiple visual chart models as the optimal chart model.

4. The auxiliary access method applied to the railway signal centralized monitoring system according to claim 3 is characterized in that: In the step S30, the relevant data parameters are marked in the optimal chart model to obtain an optimal visualization chart; and whether there are abnormal data parameters in the relevant data parameters is determined. If so, the abnormal data parameters are highlighted on the optimal visualization chart, and generating the abnormal data visualization chart includes: Marking one or more of the power supply data parameters, track circuit data parameters, switch data parameters, signal data parameters, and signal equipment working environment parameters in the optimal chart model to obtain an optimal visualization chart; Parameter threshold ranges are preset for the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters respectively. When one or more of the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters exceed the parameter threshold ranges, it is determined that abnormal data parameters exist in the relevant data parameters, the abnormal data parameters are highlighted and / or animatedly flashing on the optimal visualization chart, and an abnormal data visualization chart is generated based on the abnormal data parameters.

5. The auxiliary access method applied to the railway signal centralized monitoring system according to claim 4 is characterized in that: In step S40, machine learning is performed on the abnormal data parameters to locate the fault point and analyze the fault cause; based on the fault cause, generating a fault prediction tree centered on the fault point includes: Collect a large amount of historical abnormal data parameters for machine learning to generate a fault analysis model, input the abnormal data parameters into the fault analysis model, locate the fault point and output the fault cause; Based on the fault cause, the fault path is derived through a Bayesian network or a decision tree to generate a fault prediction tree centered on the fault point.

6. The auxiliary reading system applied to the railway signal centralized monitoring system is characterized by: It includes the following modules: Identity recognition module, used to identify user identity information and determine whether the user has access permission; A demand triggering module is used to trigger a retrieval demand and obtain relevant data features and relevant data parameters based on the retrieval demand; A chart matching module, configured to automatically match a plurality of visual chart models for a user based on the relevant data features; a chart confirmation module, configured to determine an optimal chart model based on the multiple visual chart models; a chart visualization module, configured to mark the relevant data parameters in the optimal chart model to obtain an optimal visualization chart; and determine whether there are abnormal data parameters in the relevant data parameters. If so, highlight the abnormal data parameters on the optimal visualization chart and generate an abnormal data visualization chart; The potential fault prediction module is used to perform machine learning on the abnormal data parameters, locate the fault point and predict the cause of the abnormality; based on the cause of the abnormality, generate a fault prediction tree centered on the fault point.

7. The auxiliary reading system for railway signal centralized monitoring system according to claim 6, characterized in that: The identity recognition module is used to identify the user's identity information and determine whether the user has access permission, including: Creating an identity information database, identifying and judging the user's identity information; if the user's identity information exists in the identity information database, then judging that the user has access rights; if the user's identity information does not exist in the identity information database, then judging that the user does not have access rights; The demand triggering module is used to trigger the access demand, and obtains relevant data features and relevant data parameters based on the access demand, including: If the user has access permission, the user inputs access information to trigger the access demand, and natural language processing technology is used to perform semantic recognition on the access information to obtain the relevant data features and relevant data parameters required by the user; wherein, the relevant data features include access type features, access field features and access intention features, and the relevant data parameters include power supply data parameters, track circuit data parameters, turnout data parameters, signal data parameters and signal equipment working environment parameters.

8. The auxiliary reading system for railway signal centralized monitoring system according to claim 7, characterized in that: The chart matching module is used to automatically match multiple visual chart models for the user based on the relevant data features, including: Collect railway industry standard charts and create a chart model database, wherein the railway industry standard charts include statistical charts, heat matrix charts, sunburst charts, and radar charts; based on the query type characteristics, query field characteristics, and query intention characteristics, configure chart matching rules using a rule engine; match railway industry standard charts in the chart model database based on the chart matching rules to obtain a matching confidence; when the matching confidence exceeds a confidence threshold, determine that the corresponding railway industry standard chart is a visual chart model; The chart confirmation module is configured to determine the best chart model based on the multiple visual chart models, including: The multiple visual chart models are displayed in descending order of the matching confidence, and the user selects the visual chart model that best meets his / her usage habits from the multiple visual chart models as the optimal chart model.

9. The auxiliary reading system for railway signal centralized monitoring system according to claim 8, characterized in that: The chart visualization module is configured to mark the relevant data parameters in the optimal chart model to obtain an optimal visualization chart; and determine whether there are abnormal data parameters in the relevant data parameters. If so, the abnormal data parameters are highlighted on the optimal visualization chart, and the generation of the abnormal data visualization chart includes: Marking one or more of the power supply data parameters, track circuit data parameters, switch data parameters, signal data parameters, and signal equipment working environment parameters in the optimal chart model to obtain an optimal visualization chart; Parameter threshold ranges are preset for the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters respectively. When one or more of the power supply data parameters, track circuit data parameters, turnout and switch data parameters, signal data parameters and signal equipment working environment parameters exceed the parameter threshold ranges, it is determined that abnormal data parameters exist in the relevant data parameters, the abnormal data parameters are highlighted and / or animatedly flashing on the optimal visualization chart, and an abnormal data visualization chart is generated based on the abnormal data parameters.

10. The auxiliary reading system for railway signal centralized monitoring system according to claim 9, characterized in that: The potential fault prediction module is configured to perform machine learning on the abnormal data parameters, locate the fault point, and analyze the fault cause; based on the fault cause, generating a fault prediction tree centered on the fault point includes: Collect a large amount of historical data parameters for machine learning to generate a fault analysis model, input the abnormal data parameters into the fault analysis model, locate the fault point and output the fault cause; Based on the fault cause, the fault path is derived through a Bayesian network or a decision tree to generate a fault prediction tree centered on the fault point.

Images