Method and device for determining train delay state and readable storage medium

Abstract

The invention provides a train delay state determination method and device and a readable storage medium. The train delay state determination method comprises the steps that moment data of a first train in a whole-course transportation chain and actual track data of the first train in the whole-course transportation chain are obtained; acquiring a first track sequence of the first train; on the basis of the first track sequence and the time data, delay data and stop deviation data of each station of the first train in the whole-course transportation chain are determined; according to the multiple pieces of delay data and the stay deviation data, determining an abnormal stay site; according to the multiple pieces of delay data, obtaining a section delay value of each transportation section and a contribution index of each transportation section; determining delay data of the first train on the whole-course transportation chain according to the abnormal stop stations, the plurality of section delay values and the plurality of contribution degree indexes; and according to the delay data, determining estimated delay data of the second train on the whole-course transportation chain. The optimization efficiency is improved according to the delay condition analysis of the site and the section level.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a train delay state determination method, device and readable storage medium. BACKGROUND

[0002] In the prior art, when the delay of a train is determined, overall delay detection is performed by using historical average time data, so that the display page of the client can only determine the delay of the train at a fixed station, and can only determine whether the train is delayed, but cannot accurately locate the section or station causing the delay, thereby affecting the pertinence of operation optimization and reducing the optimization efficiency of the delay of the train operation. SUMMARY

[0003] The present application aims to at least solve one of the problems in the prior art or related art.

[0004] To this end, the first aspect of the present application provides a train delay state determination method.

[0005] The second aspect of the present application provides a train delay state determination device.

[0006] The third aspect of the present application provides a train delay state determination device.

[0007] The fourth aspect of the present application provides a readable storage medium.

[0008] Therefore, according to the first aspect of the present application, a train delay state determination method is provided, which is used for a server, and includes: acquiring time data of a first train in a whole transport chain and actual trajectory data of the first train in the whole transport chain, the whole transport chain including a plurality of transport sections, wherein the first train is a train that has completed operation; acquiring a first trajectory sequence of the first train according to the time data and the actual trajectory data; determining delay data and stay deviation data of each station in the whole transport chain of the first train based on the first trajectory sequence and the time data, wherein the stay deviation data is used to represent the difference between the actual stay duration of the first train at each station and the planned stay duration; determining an abnormal stay station according to a plurality of delay data and stay deviation data; acquiring a section delay value of each transport section and a contribution degree index of each transport section according to a plurality of delay data, wherein the contribution degree index is used to represent the influence degree of each transport section on the total delay of the whole transport chain; determining delay data of the first train on the whole transport chain according to the abnormal stay station, a plurality of section delay values and a plurality of contribution degree indexes; and determining estimated delay data of a second train on the whole transport chain according to the delay data, wherein the second train is a train to be operated.

[0009] The train delay state determination method provided in the application is used for a server, and comprises the following steps:

[0010] Obtain time data of the first train in the whole transport chain and actual trajectory data of the first train in the whole transport chain, wherein the whole transport chain comprises a plurality of transport sections, the first train is a train that has completed operation, and the first train is a train that runs across regions. The time data is a planned timetable of the first train in a completed operation shift or an ongoing operation shift. The actual trajectory data is actual trajectory information of a container on the first train and master data of all stations in the whole transport chain. The above data can be collected from a plurality of data sources, and the specific data sources include an operation group responsible for train operation or a positioning system and the like.

[0011] According to the time data and the actual trajectory data, a first trajectory sequence of the first train is obtained, the first trajectory sequence is data obtained by uniformly processing time data and actual trajectory data from different sources, and the first trajectory sequence comprises an accurate running trajectory of the first train. The obtained first trajectory sequence is data after cleaning and alignment, which is convenient for data processing.

[0012] Based on the first trajectory sequence and the time data, delay data and stay deviation data of each station in the whole transport chain of the first train are determined, and the stay deviation data is used to represent the difference between the actual stay duration and the planned stay duration of the first train at each station. The first trajectory sequence comprises time data of actual arrival and actual departure of the first train, and the time data comprises time data of planned arrival and planned departure. On this basis, the first trajectory sequence and the time data further comprise actual stay duration and planned stay duration, and automatically compare business rules, so as to mark the current station as "abnormal" when the deviation exceeds a certain threshold of the planned value. The specific threshold can be ±25%. That is, according to a plurality of delay data and stay deviation data, an abnormal stay station is determined.

[0013] Since the delay data records the delay of the first train in the whole transportation chain, according to the plurality of delay data, the segment delay value of each transportation segment and the contribution index of each transportation segment can be obtained, wherein the contribution index is used to represent the influence degree of each transportation segment on the total delay of the whole transportation chain; according to the abnormal stay station, the plurality of segment delay values and the plurality of contribution indexes, the delay data of the first train in the whole transportation chain is determined; according to the delay data, the estimated delay data of the second train in the whole transportation chain is determined, wherein the second train is a train to be run. The train delay state determination method provided by the technical scheme of the present application can effectively solve the problems of single data utilization, rough analysis granularity, disjointed business rules and insufficient path matching capability in cross-regional train delay analysis. By obtaining the time data and actual trajectory data of the first train and generating the first trajectory sequence, multi-source heterogeneous data fusion and accurate trajectory matching are realized, multi-source data is cleaned and aligned by using geographic coding and fuzzy matching algorithm, that is, the planned timetable, actual trajectory and station master data are processed, the matching problem caused by inconsistent data and station alias is solved, a complete and reliable data basis can be constructed for subsequent analysis, the coverage and accuracy of the delay analysis are improved, and the leap from single data prediction to multi-source data fusion analysis is realized.

[0014] By calculating the delay data and the stay deviation data of each station, the abnormal stay station is determined, and the segment delay value and the contribution index of each transportation segment are obtained, and the station and segment delay contribution analysis is completed. The whole delay can be dynamically decomposed to the station and segment levels, the abnormal stay and segment contribution degree are determined based on the business rules by quantifying the stay deviation, the bottleneck link and the responsibility interval in the whole transportation chain are accurately located, the deepening from the overall delay prediction to the segmented delay attribution is realized, and specific guidance is provided for operation optimization.

[0015] Specifically, the comprehensive delay data is determined in combination with the abnormal stay station, the segment delay value and the contribution index, a business rule engine (such as a punctual window and a stay deviation threshold) is embedded, the output result has high business explainability, for example, the abnormal station and the segment contribution degree are automatically marked, the operation decision is directly supported, and the transformation from the general model output to the business rule embedding is realized.

[0016] In addition, the trajectory sequence generation process deals with non-standard data and path changes through intelligent trajectory reconstruction, ensures the adaptability and stability of the system in complex scenarios, and avoids misjudgment caused by data noise.

[0017] Finally, based on the delay data of the first train, the estimated delay data of the second train is predicted, and through the historical analysis result to guide the future operation, the prediction and decision support ability of the system can be enhanced, thereby improving the practicability, robustness and business value of the cross-regional train delay rate calculation as a whole. At the same time, the historical analysis result obtained by analysis, that is, the estimated delay data can reduce the risk of future train delay prediction and improve the accuracy of prediction.

[0018] In some technical solutions, optionally, the time point data of the first train in the whole transportation chain and the actual trajectory data of the first train in the whole transportation chain are obtained by: collecting raw data about the running of the first train on the whole transportation chain from a plurality of heterogeneous data sources, the raw data including time point data, actual container trajectory of the first train and site data in the whole transportation chain; and obtaining the time point data of the train in the whole transportation chain and the actual trajectory data of the train in the whole transportation chain according to the time point data, the actual container trajectory of the first train and the site data in the whole transportation chain.

[0019] In the technical solutions of the present application, raw data about the running of the first train on the whole transportation chain is collected from a plurality of heterogeneous data sources, the raw data including time point data, actual container trajectory of the first train and site data in the whole transportation chain; and the time point data of the train in the whole transportation chain and the actual trajectory data of the train in the whole transportation chain are obtained according to the time point data, the actual container trajectory of the first train and the site data in the whole transportation chain, which improves the data quality and consistency, accelerates data reception through multi-thread or distributed system parallel processing, and reduces parsing time using format conversion, providing reliable structured input for subsequent site and section level delay analysis, overcoming the low coverage and misjudgment risk caused by relying on a single data source in traditional methods, thereby supporting the fine upgrading of the whole system from macro delay judgment to micro attribution.

[0020] In some technical solutions, optionally, the first trajectory sequence of the first train is obtained according to the time point data and the actual trajectory data by: mapping the original site name in the actual trajectory data to a standard site through a fuzzy matching algorithm based on geographic coding and string similarity according to the time point data and the actual trajectory data, wherein the fuzzy matching algorithm includes calculating string similarity score and geographic coordinate verification; and determining the first trajectory sequence based on the standard site, wherein the first trajectory sequence contains the actual arrival time and the actual departure time of each standard site.

[0021] In the technical solution of the present application, according to the time data and the actual trajectory data, the first trajectory sequence of the first train is obtained, including: according to the time data and the actual trajectory data, through a fuzzy matching algorithm based on geographic coding and string similarity, the original station name in the actual trajectory data is mapped to a standard station, wherein the fuzzy matching algorithm includes calculating the string similarity score and performing geographic coordinate verification; based on the standard station, the first trajectory sequence is determined, wherein the first trajectory sequence contains the actual arrival time and the actual departure time of each standard station. Through the fuzzy matching algorithm based on geographic coding and string similarity algorithm, the original station name in the actual trajectory data is mapped to a standard station, and geographic coordinate verification is performed, effectively solving the problem of inconsistent station names and inconsistent data in multi-source data, thereby reconstructing the accurate first trajectory sequence (containing the actual arrival time and the actual departure time of each standard station), improving the data quality and consistency, avoiding trajectory matching errors caused by data noise or aliases, providing high-quality, standardized input basis for subsequent station-level delay calculation (such as stay deviation analysis) and section-level contribution analysis, directly overcoming the defects of the prior art that the train trajectory cannot be accurately matched due to disordered data, and ensuring the coverage and accuracy of delay analysis.

[0022] Specifically, in the data cleaning and station normalization process, for each collected original station name S raw , the station mapping is completed through the calculation of string similarity and geographic coordinate verification method, that is, it is mapped to a standard station S std :

[0023] First, calculate the string similarity: use the edit distance algorithm to calculate the similarity score of the original station name and all candidate station names in the standard library.

[0024] Secondly, through geographic coordinate verification, for the candidate stations with similarity higher than the threshold (such as 0.8), further verify the spatial proximity (proximity) of the latitude and longitude coordinates of the train trajectory points in the positioning system.

[0025] Finally, the standard station with the highest comprehensive score of similarity and spatial proximity is matched.

[0026] The determined first trajectory sequence includes trajectory sequence reconstruction: the normalized station events are sorted according to EventDateTime (event date and time) to form the actual trajectory sequence T actual of the train {S1, S2…S n}, wherein each S n name contains a standard station identifier, an actual arrival time AT i , and an actual departure time DT iFurther, it fundamentally solves the problem of inaccurate matching of train track due to disordered data, and provides clean and consistent structured data for the entire system, which is the premise of subsequent site and section level fine calculation, and directly determines the coverage and accuracy of analysis.

[0027] In some technical solutions, optionally, the abnormal stay station is determined according to the plurality of delay data and the stay deviation data, comprising: obtaining a preset business rule, the preset business rule comprising a on-time judgment rule; determining the abnormal stay station based on the preset business rule, the plurality of delay data and the stay deviation data.

[0028] In the technical solutions of the present application, by obtaining the preset business rule (such as the reasonable window of -2 hours to +4 hours in the on-time judgment rule, and the stay deviation threshold is set to ±25% of the planned value), the system converts industry experience into calculable judgment logic. For example, when the system detects that the absolute value of the stay deviation value D stay (i) of a certain station is greater than 0.25* (ST depart (i)-ST arrive (i)), the system automatically marks the station as an abnormal stay, so that the technical analysis result is highly consistent with the business cognition, and the problem of abstract output result and disconnection with business is solved. Wherein, ST arrive (i) represents the planned arrival time of the train at station i, and STdepart(i) represents the planned departure time of the train at station i.

[0029] The determination of the abnormal station is based on the comprehensive delay data, that is, the multi-dimensional analysis of the arrival delay, the departure delay and the stay deviation data. Even if the departure delay of the station is small, but the stay deviation is significantly over-standard (such as planned stay 2 hours, actual stay 5 hours), the system avoids misjudgment through cross verification. Based on the automatic determination of the business rule, the system can count the proportion of the train that is marked as an abnormal stay at a certain station, form a station delay rate index, and help the operator to quickly locate the high-frequency problem node.

[0030] In some technical solutions, the plurality of transportation sections of the whole transportation chain are dynamically divided through key nodes; the key nodes at least include cross-regional nodes and transshipment stations.

[0031] In the technical solutions of the present application, through the key nodes such as cross-regional nodes and transshipment stations, the dynamic division of the whole transportation chain into a plurality of transportation sections can realize the fine analysis of delay and accurate positioning of responsibility.

[0032] Firstly, the key nodes are natural dividing points, such as the port station marking the cross-regional boundary and the transshipment station indicating the operation conversion, so that the system can adapt to the actual path changes of different trains, dynamically generate sections (such as preset regional sections, port sections and regional sections), and avoid the rigidity of fixed division.

[0033] Secondly, the division of the section supports the section-level delay calculation, which accurately identifies the bottleneck link by quantifying the delay value and contribution index of each section, thereby avoiding the problem of being unable to locate the delay source.

[0034] In addition, dynamic division is integrated with business rules to provide data basis for cross-organizational responsibility definition, such as distinguishing between preset areas and overseas operator responsibilities, and visually displaying the section impact through a visualization module, thereby ultimately improving the pertinence and efficiency of operation optimization.

[0035] In some technical solutions, optionally, according to the plurality of delay data, the section delay value of each transportation section is obtained, including: according to the delay data, determining the difference between the arrival delay of the terminal station and the departure delay of the starting station in each transportation section; according to the difference, calculating the section delay value of each transportation section, wherein the section delay value is used to represent the net delay generated in the transportation section.

[0036] In the technical solutions of the present application, the section delay value is obtained by calculating the difference between the arrival delay of the terminal station and the departure delay of the starting station in each transportation section, which realizes the accurate quantification of the section-level net delay. First, by isolating the delay influence of the section itself, the conduction interference of the previous section delay is avoided, thereby providing a more pure delay responsibility positioning, supporting fine attribution analysis, and helping the operator to identify the bottleneck link (such as a certain port section with a contribution degree of more than 60%), thereby optimizing resource allocation.

[0037] In some technical solutions, optionally, the train delay state determination method further includes generating a train delay state page according to the estimated delay data; wherein the train delay state page includes integrated visualization components, and the visualization components include a station-level abnormal alarm list and a section contribution degree waterfall chart.

[0038] In the technical solutions of the present application, the train delay state determination method further includes generating a train delay state page according to the estimated delay data; wherein the train delay state page includes integrated visualization components, and the visualization components include a station-level abnormal alarm list and a section contribution degree waterfall chart.

[0039] The visualization component converts abstract delay data into intuitive business insights through the collaborative display of the site-level anomaly alert list and the section contribution waterfall chart. The anomaly alert list dynamically marks problem sites based on preset business rules (such as stay deviation exceeding threshold) and presents the site name, deviation value, and frequency of occurrence in highlighted form. The section contribution waterfall chart visually displays the contribution percentage of each section (such as the port section and the preset regional section) to the total delay through horizontal bar charts, forming a macro and micro linked visualization logic. This allows users to quickly grasp the overall picture of the delay, for example, by discovering that a certain port section contributes 60% to the delay through the waterfall chart, and then drilling down to the alert list to confirm that there is a persistent abnormal stay at the port station, thereby accurately locating the bottleneck link.

[0040] The business rule engine embedded in the page converts industry standards (such as on-time window and deviation threshold) into dynamic judgment logic for the visualization component. For example, when the total delay exceeds the on-time window of -2 to +4 hours, the page automatically triggers a color warning. Users can drill down to the site detail view by interacting with the page (such as clicking on a specific section of the waterfall chart) to view historical delay trends and associated factors (such as weather and customs policy). This design solves the problem of abstract output and disconnection from business cognition in existing technologies, allowing technical analysis to be deeply integrated into operational scenarios and improving decision-making efficiency by about 40%.

[0041] The page generated based on estimated delay data not only reflects the historical delay status, but also supports risk warning for the second train in the future. For example, the system compares historical abnormal site patterns with current prediction data, marks high-risk sections in the page, and provides optimization suggestions (such as adjusting port operation shifts), which are suitable for collaborative optimization of complex transportation scenarios such as cross-regional trains.

[0042] The second aspect of the present application provides a train delay state determination device, the train delay state determination device is used for a server, and the device comprises a first acquisition module, a second acquisition module and a first processing module; the first acquisition module is used for acquiring time point data of a first train in a whole transportation chain and actual trajectory data of the first train in the whole transportation chain, the whole transportation chain comprises a plurality of transportation sections, wherein the first train is a train that has completed running; the second acquisition module is used for acquiring a first trajectory sequence of the first train according to the time point data and the actual trajectory data; the first processing module is used for determining delay data and stay deviation data of the first train at each station in the whole transportation chain based on the first trajectory sequence and the time point data, wherein the stay deviation data is used for representing a difference between an actual stay duration of the first train at each station and a planned stay duration; the first processing module is further used for determining an abnormal stay station according to a plurality of delay data and stay deviation data; the first processing module is further used for acquiring a section delay value of each transportation section and a contribution degree index of each transportation section according to a plurality of delay data, wherein the contribution degree index is used for representing an influence degree of each transportation section on total delay of the whole transportation chain; the first processing module is further used for determining delay data of the first train on the whole transportation chain according to the abnormal stay station, a plurality of section delay values and a plurality of contribution degree indexes; and the first processing module is further used for determining estimated delay data of a second train on the whole transportation chain according to the delay data, wherein the second train is a train to be run.

[0043] The application provides a train delay state determination device, which is used for a server and comprises a first acquisition module, a second acquisition module and a first processing module. The first acquisition module is used for acquiring time point data of a first train in a whole transportation chain and actual track data of the first train in the whole transportation chain. The whole transportation chain comprises a plurality of transportation sections. The first train is a train that has completed running. The second acquisition module is used for acquiring a first track sequence of the first train according to the time point data and the actual track data. The first processing module is used for determining delay data and stay deviation data of each station of the first train in the whole transportation chain based on the first track sequence and the time point data. The stay deviation data is used for representing the difference between the actual stay duration and the planned stay duration of the first train at each station. The first processing module is further used for determining an abnormal stay station according to a plurality of delay data and stay deviation data. The first processing module is further used for acquiring a section delay value of each transportation section and a contribution degree index of each transportation section according to a plurality of delay data, wherein the contribution degree index is used for representing the influence degree of each transportation section on the total delay of the whole transportation chain. The first processing module is further used for determining delay data of the first train on the whole transportation chain according to the abnormal stay station, a plurality of section delay values and a plurality of contribution degree indexes. The first processing module is further used for determining estimated delay data of a second train on the whole transportation chain according to the delay data, wherein the second train is a train to be run. The first acquisition module collects the planned time table and the actual track data from a plurality of source heterogeneous data sources, solves the data island problem and improves the reliability of the data basis. The second acquisition module reconstructs a standardized track sequence through geographic coding and string similarity algorithm, and ensures the station matching accuracy. The first processing module calculates the station level delay data, the stay deviation data and the section level contribution degree index based on the business rules, accurately locates the delay root cause (such as the contribution degree of the port section is more than 60%), and generates the estimated delay data to support the risk prediction of the second train (the train to be run). The train delay state determination device deeply integrates the multi-source data fusion, the fine calculation and the business rules, overcomes the limitation that the prior art can only macroscopically judge the delay, realizes the closed loop from data collection to decision support, and significantly improves the operation optimization efficiency and the cross-organization collaboration ability.

[0044] The third aspect of the application provides a train delay state determination device, which comprises a processor and a memory. The memory stores programs or instructions. When the processor executes the programs or instructions in the memory, the steps of the train delay state determination method in any one of the above technical solutions are implemented. Therefore, the train delay state determination device has all the beneficial effects of the train delay state determination method in any one of the above technical solutions.

[0045] The fourth aspect of the present application provides a readable storage medium, and the readable storage medium stores programs or instructions, and the programs or instructions are executed by a processor to realize the steps of the train delay state determination method in any one of the above technical solutions. Therefore, the readable storage medium has all the beneficial effects of the train delay state determination method in any one of the above technical solutions.

[0046] Additional aspects and advantages of the present application will be described in the following description and will be apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0047] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood by considering the following detailed description, from which the singular features of the application will be more clearly understood.

[0048] Figure 1 One of flowcharts of a train delay state determination method provided in some embodiments of the present application is shown;

[0049] Figure 2 A schematic diagram of a train delay state page provided in some embodiments of the present application is shown;

[0050] Figure 3 One of structural block diagrams of a train delay state determination apparatus provided in some embodiments of the present application is shown;

[0051] Figure 4 The second structural block diagram of a train delay state determination apparatus provided in some embodiments of the present application is shown;

[0052] Figure 5 The second flowchart of a train delay state determination method provided in some embodiments of the present application is shown;

[0053] Figure 6 The third flowchart of a train delay state determination method provided in some embodiments of the present application is shown. DETAILED DESCRIPTION

[0054] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0055] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, however, the present application can also be implemented in other ways different from those described herein, therefore, the scope of protection of the present application is not limited by the specific embodiments disclosed below.

[0056] The following description refers to the accompanying drawings. Figures 1 to 6 A method, device and readable storage medium for determining a train delay status are described according to some embodiments of the present application.

[0057] As shown in Figure 1 The embodiments of the present application provide a method for determining a train delay status, the method for determining a train delay status is used for a server, and steps of the method for determining a train delay status include the following steps.

[0058] In step 102, time point data of a first train in a whole transportation chain and actual trajectory data of the first train in the whole transportation chain are acquired, and the whole transportation chain includes a plurality of transportation sections, and the first train is a train that has completed running.

[0059] In step 104, a first trajectory sequence of the first train is acquired according to the time point data and the actual trajectory data.

[0060] In step 106, delay data and stay deviation data of the first train at each station in the whole transportation chain are determined based on the first trajectory sequence and the time point data, and the stay deviation data is used to represent a difference between an actual stay duration and a planned stay duration of the first train at each station.

[0061] In step 108, an abnormal stay station is determined according to a plurality of delay data and stay deviation data.

[0062] In step 110, a section delay value of each transportation section and a contribution degree index of each transportation section are acquired according to a plurality of delay data, and the contribution degree index is used to represent an influence degree of each transportation section on a total delay of the whole transportation chain.

[0063] In step 112, delay data of the first train on the whole transportation chain is determined according to the abnormal stay station, a plurality of section delay values and a plurality of contribution degree indexes.

[0064] In step 114, estimated delay data of a second train on the whole transportation chain is determined according to the delay data, and the second train is a train to be run.

[0065] The method for determining a train delay status provided by the present application is used for a server, and the method for determining a train delay status includes the following steps.

[0066] Obtaining time data of a first train in a whole transportation chain and actual trajectory data of the first train in the whole transportation chain, the whole transportation chain including a plurality of transportation sections, wherein the first train is a train that has completed operation. The first train is a train that runs across regions, and the time data is a planned timetable of the first train in a completed operation shift or an ongoing operation shift. The actual trajectory data is actual trajectory information of a container on the first train and master data of all stations in the whole transportation chain, and the above data can be collected from a plurality of data sources, including an operation group responsible for train operation or a positioning system and the like.

[0067] According to the time data and the actual trajectory data, a first trajectory sequence of the first train is obtained, the first trajectory sequence being data obtained by uniformly processing time data and actual trajectory data of different sources, and the first trajectory sequence including an accurate running trajectory of the first train. The obtained first trajectory sequence is data after cleaning and alignment, facilitating data processing.

[0068] Based on the first trajectory sequence and the time data, delay data and stay deviation data of each station of the first train in the whole transportation chain are determined, the stay deviation data being used to represent the difference between the actual stay duration of the first train at each station and the planned stay duration. The first trajectory sequence includes time data of actual arrival and actual departure of the first train, and the time data includes time data of planned arrival and planned departure, on the basis of which the first trajectory sequence and the time data further include actual stay duration and planned stay duration, and automatically compare business rules, and then mark the current station as "abnormal" when the deviation exceeds a certain threshold of the planned value. The specific threshold can be ±25%. That is, according to a plurality of delay data and stay deviation data, an abnormal stay station is determined.

[0069] Since the delay data records the delay of the first train in the whole transportation chain, according to the plurality of delay data, a segment delay value of each transportation segment and a contribution index of each transportation segment can be obtained, wherein the contribution index is used to represent the influence degree of each transportation segment on the total delay of the whole transportation chain; according to the abnormal stay station, the plurality of segment delay values and the plurality of contribution indexes, the delay data of the first train in the whole transportation chain is determined; according to the delay data, the estimated delay data of the second train in the whole transportation chain is determined, wherein the second train is a train to be run. The train delay state determination method provided in the embodiment of the application can effectively solve the problems of single data utilization, rough analysis granularity, disconnection of business rules and insufficient path matching capability in cross-regional train delay analysis through a series of cooperatively working technical features. By obtaining the time data and actual trajectory data of the first train and generating the first trajectory sequence, multi-source heterogeneous data fusion and accurate trajectory matching are realized, multi-source data is cleaned and aligned by using geographic coding and fuzzy matching algorithm, that is, the planned timetable, actual trajectory and station master data are processed, the matching problem caused by inconsistent data and station alias is solved, a complete and reliable data basis can be constructed for subsequent analysis, the coverage and accuracy of the delay analysis are improved, and a leap from single data prediction to multi-source data fusion analysis is realized.

[0070] By calculating the delay data and the stay deviation data of each station, the abnormal stay station is determined, and the segment delay value and the contribution index of each transportation segment are obtained, and the station and segment delay contribution analysis is completed. The whole delay can be dynamically decomposed to the station and segment levels, the abnormal stay and segment contribution degree are determined based on the business rules by quantifying the stay deviation, the bottleneck link and the responsibility interval in the whole transportation chain are accurately located, the deepening from the overall delay prediction to the segmented delay attribution is realized, and specific guidance is provided for operation optimization.

[0071] Further, the comprehensive delay data is determined in combination with the abnormal stay station, the segment delay value and the contribution index, a business rule engine (such as a punctual window and a stay deviation threshold) is embedded, the output result has high business explainability, for example, the abnormal station and the segment contribution degree are automatically marked, the operation decision is directly supported, and the transformation from the general model output to the business rule embedding is realized.

[0072] In addition, the trajectory sequence generation process deals with non-standard data and path changes through intelligent trajectory reconstruction, ensures the adaptability and stability of the system in complex scenarios, and avoids misjudgment caused by data noise.

[0073] Finally, based on the delay data of the first train, the estimated delay data of the second train is predicted, and through the historical analysis result to guide the future operation, the prediction and decision support ability of the system can be enhanced, thereby improving the practicability, robustness and business value of the cross-regional train delay rate calculation as a whole. At the same time, the historical analysis result obtained by analysis, that is, the estimated delay data can reduce the risk of future train delay prediction and improve the accuracy of prediction.

[0074] In some embodiments, optionally, acquiring the time point data of the first train in the whole transport chain and the actual trajectory data of the first train in the whole transport chain comprises: collecting raw data about the running of the first train on the whole transport chain from a plurality of heterogeneous data sources, the raw data including time point data, actual container trajectory of the first train and site data in the whole transport chain; acquiring the time point data of the train in the whole transport chain and the actual trajectory data of the train in the whole transport chain according to the time point data, the actual container trajectory of the first train and the site data in the whole transport chain.

[0075] In the embodiments of the present application, raw data about the running of the first train on the whole transport chain is collected from a plurality of heterogeneous data sources, the raw data including time point data, actual container trajectory of the first train and site data in the whole transport chain; the time point data of the train in the whole transport chain and the actual trajectory data of the train in the whole transport chain are acquired according to the time point data, the actual container trajectory of the first train and the site data in the whole transport chain, which improves the data quality and consistency, accelerates data reception through multi-thread or distributed system parallel processing, and reduces parsing time using format conversion, providing reliable structured input for subsequent site and section level delay analysis, overcoming the low coverage and misjudgment risk caused by relying on a single data source in traditional methods, thereby supporting the fine upgrading of the whole system from macro delay judgment to micro attribution.

[0076] In some embodiments, optionally, acquiring the first trajectory sequence of the first train according to the time point data and the actual trajectory data comprises: according to the time point data and the actual trajectory data, mapping the original site name in the actual trajectory data to a standard site through a fuzzy matching algorithm based on geographic coding and string similarity, wherein the fuzzy matching algorithm includes calculating string similarity score and geographic coordinate verification; determining the first trajectory sequence based on the standard site, wherein the first trajectory sequence contains the actual arrival time and the actual departure time of each standard site.

[0077] In the embodiments of the present application, according to the time data and the actual trajectory data, the first trajectory sequence of the first train is obtained, including: according to the time data and the actual trajectory data, through a fuzzy matching algorithm based on geographic coding and string similarity, mapping the original station name in the actual trajectory data to a standard station, wherein the fuzzy matching algorithm includes calculating a string similarity score and performing a geographic coordinate check; based on the standard station, determining the first trajectory sequence, wherein the first trajectory sequence contains the actual arrival time and the actual departure time of each standard station. Through the fuzzy matching algorithm based on geographic coding and string similarity algorithm, the original station name in the actual trajectory data is mapped to a standard station, and a geographic coordinate check is performed, effectively solving the problem of inconsistent station names and inconsistent data in multi-source data, thereby reconstructing an accurate first trajectory sequence (containing the actual arrival time and the actual departure time of each standard station), improving data quality and consistency, avoiding trajectory matching errors caused by data noise or aliases, providing high-quality, standardized input basis for subsequent station-level delay calculation (such as stay deviation analysis) and section-level contribution analysis, directly overcoming the defects of the prior art that cannot accurately match the train trajectory due to disordered data, and ensuring the coverage and accuracy of delay analysis.

[0078] Specifically, in the data cleaning and station normalization process, for each collected original station name S raw , the station mapping is completed through a string similarity calculation and a geographic coordinate check method, that is, it is mapped to a standard station S std :

[0079] First, calculate the string similarity: use the edit distance algorithm to calculate the similarity score of the original station name and all candidate station names in the standard library.

[0080] Second, through geographic coordinate check, for candidate stations with a similarity higher than a threshold (such as 0.8), further check the spatial proximity (proximity) of the latitude and longitude coordinates of the train in the positioning system.

[0081] Finally, the standard station with the highest comprehensive score of similarity and spatial proximity is matched.

[0082] The determined first trajectory sequence includes trajectory sequence reconstruction: sorting the normalized station events by EventDateTime to form the actual trajectory sequence T actual of the train {S1, S2…S n}, wherein each name S n contains a standard station identifier, an actual arrival time AT i , and an actual departure time DT iFurther, it fundamentally solves the problem of inaccurate matching of train track due to disordered data, and provides clean and consistent structured data for the entire system, which is the premise of subsequent fine calculation at the station and section level, and directly determines the coverage and accuracy of the analysis.

[0083] In some embodiments, optionally, the abnormal stay station is determined according to the plurality of delay data and the stay deviation data, comprising: obtaining a preset business rule, the preset business rule comprising a on-time judgment rule; determining the abnormal stay station based on the preset business rule, the plurality of delay data and the stay deviation data.

[0084] In the embodiments of the application, by obtaining the preset business rule (such as the reasonable window of -2 hours to +4 hours in the on-time judgment rule, and the stay deviation threshold is set to ±25% of the planned value), the system converts industry experience into calculable judgment logic. For example, when the system detects that the absolute value of the stay deviation value D stay (i) of a certain station is greater than 0.25* (ST depart (i)-ST arrive (i)), the system automatically marks the station as an abnormal stay, so that the technical analysis result is highly consistent with the business cognition, and the problem of abstract output result and disconnection with business is solved. Wherein, ST arrive (i) represents the planned arrival time of the train at station i, and STdepart(i) represents the planned departure time of the train at station i.

[0085] The determination of the abnormal station is based on the comprehensive delay data, that is, the multi-dimensional analysis of the arrival delay, the departure delay and the stay deviation data. Even if the departure delay of the station is small, but the stay deviation is significantly over-standard (such as planned stay 2 hours, actual stay 5 hours), the system avoids misjudgment through cross verification. Based on the automatic determination of the business rule, the system can count the proportion of the train that is marked as an abnormal stay at a certain station, form a station delay rate index, and help the operator to quickly locate the high-frequency problem node.

[0086] In some embodiments, optionally, the plurality of transportation sections of the whole transportation chain are dynamically divided through key nodes; the key nodes at least include cross-regional nodes and transshipment stations.

[0087] In the embodiments of the application, through the key nodes such as the cross-regional nodes and the transshipment stations, the dynamic division of the whole transportation chain into a plurality of transportation sections can realize the fine analysis of the delay and the accurate positioning of the responsibility.

[0088] Firstly, the key nodes are natural dividing points, such as the port station indicating the cross-regional boundary and the transshipment station indicating the operation conversion, so that the system can adapt to the actual path changes of different trains, dynamically generate sections (such as regional sections, port sections and regional sections), and avoid the rigidity of fixed division.

[0089] Secondly, the division of the section supports the section-level delay calculation, which accurately identifies the bottleneck link by quantifying the delay value and contribution index of each section, thereby avoiding the problem of being unable to locate the delay source.

[0090] In addition, dynamic division is integrated with business rules to provide data basis for cross-organizational responsibility definition, such as distinguishing between preset areas and overseas operator responsibilities, and visually displaying the section impact through a visualization module, thereby ultimately improving the pertinence and efficiency of operation optimization.

[0091] In some embodiments, optionally, according to the plurality of delay data, the section delay value of each transportation section is obtained, including: according to the delay data, determining the difference between the arrival delay of the terminal station and the departure delay of the starting station in each transportation section; and according to the difference, calculating the section delay value of each transportation section, wherein the section delay value is used to represent the net delay generated in the transportation section.

[0092] In the embodiments of the present application, the section delay value is obtained by calculating the difference between the arrival delay of the terminal station and the departure delay of the starting station in each transportation section, which realizes the accurate quantification of the net delay at the section level. First, by isolating the delay influence of the section itself, the conduction interference of the previous section delay is avoided, thereby providing a more pure delay responsibility positioning, supporting fine attribution analysis, and helping the operator to identify the bottleneck link (such as a certain port section with a contribution degree of more than 60%), thereby optimizing resource allocation.

[0093] In some embodiments, optionally, the method for determining the train delay state further includes generating a train delay state page according to the estimated delay data; wherein the train delay state page includes integrated visualization components, and the visualization components include a station-level abnormal alarm list and a section contribution degree waterfall chart.

[0094] In the embodiments of the present application, the method for determining the train delay state further includes generating a train delay state page according to the estimated delay data; wherein the train delay state page includes integrated visualization components, and the visualization components include a station-level abnormal alarm list and a section contribution degree waterfall chart.

[0095] The visualization component transforms abstract delay data into intuitive business insights through the collaborative display of a site-level anomaly alarm list and a segment contribution waterfall chart. The anomaly alarm list dynamically marks problematic sites based on preset business rules (such as stay deviation exceeding a threshold), highlighting the site name, deviation value, and frequency of occurrence. The segment contribution waterfall chart visually displays the percentage contribution of each segment (such as the port segment or preset regional segments) to the total delay through horizontal bar charts, forming a visualization logic that links macro and micro levels. This allows users to quickly grasp the overall delay situation; for example, after discovering that a port segment's contribution reaches 60% through the waterfall chart, users can drill down to the alarm list to confirm continuous abnormal stays at the port station, thus accurately locating the bottleneck.

[0096] The embedded business rules engine translates industry standards (such as on-time windows and deviation thresholds) into dynamic judgment logic for visual components. For example, when the total delay exceeds the on-time window of -2 to +4 hours, the page automatically triggers a color warning. Users can drill down to a detailed site view through interactive operations (such as clicking on a specific segment of the waterfall chart) to view historical delay trends and related factors (such as weather and customs policies). This design solves the problem of abstract technical output results being disconnected from business understanding, enabling technical analysis to be deeply integrated into operational scenarios and improving decision-making efficiency by approximately 40%.

[0097] The page generated based on estimated delay data not only reflects historical delay status but also supports risk warnings for future second trains. For example, by comparing historical abnormal station patterns with current predicted data, the system marks high-risk sections on the page and provides optimization suggestions (such as adjusting port operation schedules), which is suitable for collaborative optimization in complex cross-regional transportation scenarios such as cross-regional trains.

[0098] like Figure 2 As shown, Figure 2 This document demonstrates a method for determining train delay status and displays the resulting train delay status page. The page includes components for overview, segment analysis, station analysis, and data export. The route selection option on the page allows users to choose different routes, such as from station A to station B. The station status panel displays the status of stations A, C, and D. The page also includes a segment delay contribution waterfall chart, showing the percentage of delay time for segments E, F, and G.

[0099] like Figure 3As shown, the embodiments of the present application provide a train delay state determination apparatus 200, the train delay state determination apparatus 200 is used for a server, and the apparatus comprises a first acquisition module 202, a second acquisition module 204 and a first processing module 206; the first acquisition module 202 is used for acquiring time point data of a first train in a whole transportation chain and actual track data of the first train in the whole transportation chain, the whole transportation chain comprises a plurality of transportation sections, wherein the first train is a train that has completed running; the second acquisition module 204 is used for acquiring a first track sequence of the first train according to the time point data and the actual track data; the first processing module 206 is used for determining delay data and stay deviation data of the first train at each station in the whole transportation chain based on the first track sequence and the time point data, wherein the stay deviation data is used for representing a difference between an actual stay duration of the first train at each station and a planned stay duration; the first processing module 206 is further used for determining an abnormal stay station according to a plurality of delay data and stay deviation data; the first processing module 206 is further used for acquiring a section delay value of each transportation section and a contribution degree index of each transportation section according to a plurality of delay data, wherein the contribution degree index is used for representing an influence degree of each transportation section on total delay of the whole transportation chain; the first processing module 206 is further used for determining delay data of the first train on the whole transportation chain according to the abnormal stay station, a plurality of section delay values and a plurality of contribution degree indexes; the first processing module 206 is further used for determining estimated delay data of a second train on the whole transportation chain according to the delay data, wherein the second train is a train to be run.

[0100] The application provides a train delay state determination device 200, which is used for a server and comprises a first acquisition module 202, a second acquisition module 204 and a first processing module 206. The first acquisition module 202 is used for acquiring time point data of a first train in a whole transportation chain and actual track data of the first train in the whole transportation chain. The whole transportation chain comprises a plurality of transportation sections. The first train is a train that has completed running. The second acquisition module 204 is used for acquiring a first track sequence of the first train according to the time point data and the actual track data. The first processing module 206 is used for determining delay data and stay deviation data of each station of the first train in the whole transportation chain based on the first track sequence and the time point data. The stay deviation data is used for representing a difference between an actual stay duration and a planned stay duration of the first train at each station. The first processing module 206 is further used for determining an abnormal stay station according to a plurality of delay data and stay deviation data. The first processing module 206 is further used for acquiring a section delay value of each transportation section and a contribution degree index of each transportation section according to a plurality of delay data, wherein the contribution degree index is used for representing an influence degree of each transportation section on total delay of the whole transportation chain. The first processing module 206 is further used for determining delay data of the first train on the whole transportation chain according to the abnormal stay station, a plurality of section delay values and a plurality of contribution degree indexes. The first processing module 206 is further used for determining estimated delay data of a second train on the whole transportation chain according to the delay data, wherein the second train is a train to be run. The first acquisition module 202 collects a planned time table and actual track data from a plurality of source heterogeneous data sources, solves a data island problem and improves data basic reliability. The second acquisition module 204 reconstructs a standardized track sequence through geographic coding and string similarity algorithm and ensures station matching accuracy. The first processing module 206 calculates station level delay data, stay deviation data and section level contribution degree index based on business rules, accurately locates delay root causes (such as a contribution degree of a port section being more than 60%) and generates estimated delay data to support risk prediction of the second train (a train to be run). The train delay state determination device 200 deeply integrates multi-source data fusion, fine calculation and business rules, overcomes a limitation that the prior art can only macroscopically judge delay, realizes a closed loop from data collection to decision support, and significantly improves operation optimization efficiency and cross-organization collaboration ability.

[0101] As Figure 4 shown, the application embodiment provides a train delay state determination device 300, which comprises a processor 302 and a memory 304. The memory 304 stores programs or instructions. The processor 302 implements steps of the train delay state determination method of any one of the above embodiments when executing the programs or instructions in the memory 304. Therefore, the train delay state determination device 300 has all the beneficial effects of the train delay state determination method of any one of the above embodiments.

[0102] The embodiment of the present application provides a readable storage medium, and the readable storage medium stores programs or instructions, and the programs or instructions are executed by a processor to realize the steps of the train delay state determination method in any one of the above embodiments. Therefore, the readable storage medium has all the beneficial effects of the train delay state determination method in any one of the above embodiments.

[0103] As shown in Figure 5 The train delay state determination method provided by the present application further comprises the following steps:

[0104] In step 402, multi-source heterogeneous data is collected.

[0105] In step 404, data cleaning is performed, and a fuzzy matching algorithm is used to process text differences.

[0106] In step 406, a standardized station event sequence is formed.

[0107] In step 408, a track sequence alignment algorithm is used to reconstruct a complete track of a train.

[0108] In step 410, standardized track data is output.

[0109] The train delay state determination method is used to clean and process data.

[0110] As shown in Figure 6 The train delay state determination method provided by the present application further comprises the following steps:

[0111] In step 502, standardized track data is input.

[0112] In step 504, station delay is calculated.

[0113] In step 506, transportation sections are automatically divided.

[0114] In step 508, delay values of the sections are calculated.

[0115] In step 510, a delay contribution percentage of each section is calculated.

[0116] In step 512, station and section delay analysis results are output.

[0117] First, the step 502 inputs standardized trajectory data, ensuring high-quality basis after cleaning and normalization of multi-source heterogeneous data, providing reliable input for subsequent analysis; then, the step 504 calculates the station delay, quantifies the arrival delay, departure delay and stay deviation of each station, and accurately identifies the abnormal link at the micro level; the step 506 automatically divides the transport section based on the key node (such as the port), dynamically adapts to the actual running path, and overcomes the rigidity of fixed division; then, the step 508 calculates the delay value of each section, and the net delay is reflected by the difference between the end and start delay of the section, and the step 510 further calculates the delay contribution percentage of each section, quantifying the influence weight of each section on the total delay, and realizing the macro delay responsibility positioning together; finally, the step 512 outputs the station and section delay analysis results, integrates the visualization components (such as the abnormal station list and the contribution waterfall chart), and converts technical data into business understandable insights, supporting the decision-making closed loop from abnormal diagnosis to resource optimization, and improving the accuracy, explainability and operation efficiency of delay analysis as a whole.

[0118] In the claims, the specification, and the drawings of the present application, terms "multiple" means two or more, unless otherwise expressly specified and limited by context, terms "upper", "lower", and the like mean directions or positions relative to the directions or positions shown in the drawings for convenience in describing the present application and simplifying the description, and therefore these descriptions cannot be understood as limiting the present application in terms of the specific directions or positions, configurations and operations, and therefore these descriptions cannot be understood as limiting the present application in terms of the specific directions or positions, configurations and operations; terms "connection", "installation", "fixation" and the like should be understood in a broad sense, for example, "connection" can be fixed connection between objects, or detachable connection between objects, or integral connection; can be direct connection between objects, or indirect connection between objects through intermediate medium. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances of the above data.

[0119] In the claims, the specification, and the drawings of the present application, the description of terms "one embodiment", "some embodiments", "a specific embodiment" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the claims, the specification and the drawings of the present application, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0120] The above merely provides the preferred embodiments of the present application, and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the principles and technical scope of the present application shall fall into the scope of the present application.

Claims

1. A method for determining train delay status, characterized in that, The method for determining the train delay status is used by a server, and the method for determining the train delay status includes: The system acquires the time data of the first train within the entire transportation chain, as well as the actual trajectory data of the first train within the entire transportation chain. The entire transportation chain includes multiple transportation sections, and the first train is a train that has completed its operation. Based on the time data and the actual trajectory data, the first trajectory sequence of the first train is obtained; Based on the first trajectory sequence and the time data, the delay data and dwell deviation data of the first train at each station in the entire transportation chain are determined, wherein the dwell deviation data is used to characterize the difference between the actual dwell time and the planned dwell time of the first train at each station; Based on the multiple delay data and the stay deviation data, the abnormal stay stations are determined; Based on multiple delay data, obtain the segment delay value of each transportation segment and the contribution index of each transportation segment, wherein the contribution index is used to characterize the degree of influence of each transportation segment on the total delay of the entire transportation chain; Based on the abnormal stopping stations, multiple section delay values, and multiple contribution indicators, the delay data of the first train on the entire transportation chain is determined; Based on the delay data, the estimated delay data for the second train on the entire transportation chain is determined, wherein the second train is the train to be operated.

2. The method for determining train delay status according to claim 1, characterized in that, The acquisition of the time data of the first train within the entire transportation chain, and the actual trajectory data of the first train within the entire transportation chain, includes: Raw data about the first train running on the entire transportation chain is collected from multiple heterogeneous data sources. The raw data includes time data, the actual trajectory of the first train's containers, and station data within the entire transportation chain. Based on the time data, the actual trajectory of the first train's container, and the station data within the entire transportation chain, the time data of the train within the entire transportation chain and the actual trajectory data of the train within the entire transportation chain are obtained.

3. The method for determining train delay status according to claim 1, characterized in that, The step of obtaining the first trajectory sequence of the first train based on the time data and the actual trajectory data includes: Based on the time data and the actual trajectory data, the original station names in the actual trajectory data are mapped to standard stations using a fuzzy matching algorithm based on geocoding and string similarity. The fuzzy matching algorithm includes calculating string similarity scores and performing geographic coordinate verification. Based on the standard stations, a first trajectory sequence is determined, wherein the first trajectory sequence includes the actual arrival time and actual departure time of each of the standard stations.

4. The method for determining train delay status according to claim 1, characterized in that, The step of determining abnormal stopping stations based on multiple delay data and the stay deviation data includes: Obtain preset business rules, including on-time determination rules; Based on the preset business rules, multiple delay data, and the stay deviation data, abnormal stay stations are identified.

5. The method for determining train delay status according to claim 1, characterized in that, The entire transportation chain is dynamically divided into multiple transportation segments through key nodes; The key nodes include at least cross-regional nodes and transshipment stations.

6. The method for determining train delay status according to claim 1, characterized in that, The step of obtaining the segment delay value for each transport segment based on multiple delay data includes: Based on the delay data, determine the difference between the arrival delay of the destination station and the departure delay of the origin station within each transport segment; Based on the difference, a segment delay value is calculated for each of the transport segments, wherein the segment delay value is used to characterize the net delay generated within the transport segment.

7. The method for determining train delay status according to claim 1, characterized in that, Also includes: Based on the estimated delay data, generate a train delay status page; The train delay status page includes an integrated visualization component, which includes a station-level anomaly alarm list and a section contribution waterfall chart.

8. A device for determining train delay status, characterized in that, The device for determining the train delay status is used as a server, and the device includes: The first acquisition module is used to acquire the time data of the first train within the entire transportation chain, and the actual trajectory data of the first train within the entire transportation chain. The entire transportation chain includes multiple transportation sections, wherein the first train is a train that has completed its operation. The second acquisition module is used to acquire the first trajectory sequence of the first train based on the time data and the actual trajectory data; The first processing module is used to determine the delay data and dwell deviation data of the first train at each station in the entire transportation chain based on the first trajectory sequence and the time data, wherein the dwell deviation data is used to characterize the difference between the actual dwell time and the planned dwell time of the first train at each station; The first processing module is further configured to determine abnormal stopping stations based on multiple delay data and the stay deviation data; The first processing module is further configured to obtain the segment delay value of each of the transport segments and the contribution index of each of the transport segments based on the multiple delay data, wherein the contribution index is used to characterize the degree of influence of each transport segment on the total delay of the entire transport chain; The first processing module is further configured to determine the delay data of the first train on the entire transportation chain based on the abnormal stopping stations, multiple section delay values, and multiple contribution indicators; The first processing module is further configured to determine the estimated delay data of the second train on the entire transportation chain based on the delay data, wherein the second train is a train to be operated.

9. A device for determining train delay status, characterized in that, include: processor; A memory storing programs or instructions, wherein the processor, when executing the programs or instructions in the memory, implements the steps of the method for determining the train delay status as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method for determining the train delay status as described in any one of claims 1 to 7.

Images