Rail transit data analysis method, device and equipment and storage medium

Abstract

The invention provides a rail transit data analysis method, device and equipment and a storage medium, and the method comprises the steps: determining a key index of data needing to be collected in each signal system of rail transit according to the industrial standard and purchase information of the rail transit, and enabling the key index to represent the operation condition of the rail transit; according to the key index, initial operation data corresponding to the key index are collected in each signal system through a specified system interface and uniformly stored in a preset database; obtaining to-be-analyzed data corresponding to the to-be-analyzed key index from a preset database according to related analysis information of the to-be-analyzed key index input by a user, and performing analysis according to the related analysis information to obtain an analysis result corresponding to the to-be-analyzed key index; the related analysis information comprises a data analysis dimension, and the analysis result comprises a change trend and an abnormal item corresponding to the to-be-analyzed key index under the data analysis dimension. By adopting the technical scheme of the invention, the data analysis capability can be improved.

Description

Technical Field

[0001] This invention relates to the field of rail transit technology, and in particular to a rail transit data analysis method, apparatus, equipment, and storage medium. Background Technology

[0002] Rail transit includes various signaling systems and modules. These signaling systems and their sub-modules generate and collect data during the operation of rail vehicles, and analyzing this data can better ensure the normal operation of rail transit.

[0003] In related technologies, the data generated and collected by signal systems and their sub-modules are usually scattered across different systems or databases. Generally, it is necessary for humans to conduct separate analyses of the data in each system or database based on experience and basic statistical data in order to obtain the analysis results.

[0004] However, the aforementioned technologies suffer from insufficient analysis of rail transit data. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for rail transit data analysis, which addresses the shortcomings of existing technologies where data dispersion leads to insufficient analysis of rail transit data. It enables the collection of key indicator data from various signaling systems through designated system interfaces and centralized storage in the same database. The data in the database is then analyzed through different data analysis dimensions, improving the depth and accuracy of the obtained data analysis results. This invention is suitable for complex data analysis scenarios.

[0006] This invention provides a method for analyzing rail transit data, including: Based on industry standards and procurement information for rail transit, determine at least one key indicator that needs to be collected in each signaling system of the rail transit system; the aforementioned signaling systems include the signaling systems of each rail transit line and / or each station, and the aforementioned key indicator is used to characterize the operating status of the rail transit system. Based on the key indicators, the initial operating data corresponding to the key indicators are collected in each signal system through the designated system interface, and the initial operating data are uniformly stored in the preset database. Based on the relevant analysis information of the key indicators to be analyzed input by the user, the data to be analyzed corresponding to the key indicators to be analyzed is obtained from the preset database, and the data to be analyzed is analyzed according to the relevant analysis information to obtain the analysis results corresponding to the key indicators to be analyzed. The relevant analysis information includes data analysis dimensions, and the analysis results include the changing trends and anomalies of the key indicators to be analyzed under the data analysis dimensions.

[0007] According to a rail transit data analysis method provided by the present invention, the above-mentioned analysis of the data to be analyzed based on relevant analysis information to obtain the analysis results corresponding to the key indicators to be analyzed includes: Based on the data to be analyzed, calculate the key indicator data corresponding to the key indicators to be analyzed. Based on the data analysis dimensions in the relevant analysis information, statistical analysis is performed on the key indicator data to determine the changing trends and anomalies of the key indicators to be analyzed under the data analysis dimensions. Based on the changing trends and outliers of the key indicators to be analyzed under the data analysis dimension, the analysis results corresponding to the key indicators to be analyzed are determined.

[0008] According to a rail transit data analysis method provided by the present invention, the method further includes: Based on the type of the key indicator to be analyzed, determine at least one target visualization chart type corresponding to the key indicator to be analyzed; The analysis results corresponding to the key indicators to be analyzed are transformed into visualization charts of the target visualization chart type and then displayed.

[0009] According to a rail transit data analysis method provided by the present invention, the method further includes: Based on the changing trends and anomalies of the key indicators to be analyzed in the data analysis dimension, as well as the various fault modes of the signal system in rail transit, determine the reasons for the anomalies of the key indicators to be analyzed. Based on the reasons for the abnormality of the key indicator to be analyzed, determine and output the solution to restore the key indicator to normal.

[0010] According to a rail transit data analysis method provided by the present invention, the method further includes: Based on the analysis results, visualization charts, and solutions of the key indicators to be analyzed, generate and save the structured analysis report corresponding to the key indicators to be analyzed.

[0011] According to a rail transit data analysis method provided by the present invention, the key indicators to be analyzed include at least one of the following: Train arrival time, train delay time, false alarm rate, false alarm rate, train stopping accuracy, and transponder loss count.

[0012] According to a rail transit data analysis method provided by the present invention, when the key indicators to be analyzed include train stopping accuracy, the above-mentioned analysis of the data to be analyzed based on relevant analysis information to obtain the analysis results corresponding to the key indicators to be analyzed includes: Based on the data to be analyzed corresponding to the train stopping accuracy, calculate the stopping deviation of each train; Based on the stopping deviation of each train, determine the corresponding quantitative value of stopping accuracy for each train; The evaluation quantification value for each train is determined based on the quantitative values ​​of each stopping accuracy within a set time range and the number of times each stopping accuracy quantification value occurs. Based on the evaluation quantification value of each train, the analysis results corresponding to the train stopping accuracy are determined.

[0013] The present invention also provides a rail transit data analysis device, comprising the following modules: The indicator determination module is used to determine at least one key indicator that needs to be collected in each signaling system of the rail transit system, based on industry standards and procurement information. The signaling systems include the signaling systems of each line and / or station of the rail transit system, and the key indicators are used to characterize the operation status of the rail transit system. The data acquisition module is used to collect the initial operating data corresponding to the key indicators in each signal system through the specified system interface, and store the initial operating data in a preset database. The data analysis module is used to retrieve the data to be analyzed corresponding to the key indicators to be analyzed from a preset database based on the relevant analysis information input by the user, and to analyze the data to be analyzed based on the relevant analysis information to obtain the analysis results corresponding to the key indicators to be analyzed. The relevant analysis information includes data analysis dimensions, and the analysis results include the changing trends and anomalies of the key indicators to be analyzed under the data analysis dimensions.

[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the rail transit data analysis method as described above.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the rail transit data analysis method as described above.

[0016] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the rail transit data analysis method as described above.

[0017] The rail transit data analysis method, apparatus, equipment, and storage medium provided by this invention determine at least one key indicator that needs to be collected in each signaling system of the rail transit system based on industry standards and procurement information. According to the key indicator, initial operating data corresponding to the key indicator is collected in each signaling system through a designated system interface, and all initial operating data are uniformly stored in a preset database. Based on the relevant analysis information of the key indicator to be analyzed input by the user, the data to be analyzed corresponding to the key indicator to be analyzed is obtained from the preset database, and the data to be analyzed is analyzed according to the relevant analysis information to obtain the analysis results corresponding to the key indicator to be analyzed. The signaling system includes the signaling systems of each rail transit line and / or each station; the key indicator is used to characterize the operating status of the rail transit; the relevant analysis information includes data analysis dimensions; and the analysis results include the changing trends and anomalies corresponding to the key indicator to be analyzed under the data analysis dimensions. This method integrates data from different signal systems into a single database via a designated system interface, facilitating subsequent correlation analysis of all signal system data and enhancing the depth of data analysis. Furthermore, by identifying key indicators before collecting and storing corresponding data, the collected data becomes more targeted, leading to more accurate analysis results. Finally, analyzing key indicator data across different data analysis dimensions further enhances the depth of data analysis and the accuracy of the obtained results. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is one of the flowcharts of the rail transit data analysis method provided by the present invention; Figure 2 This is a schematic diagram of a visual chart display of train arrival and departure times provided by the present invention; Figure 3 This is a schematic diagram showing the visualization of false alarm rate and false negative rate provided by the present invention; Figure 4 This is a schematic diagram of a visual chart display of parking accuracy provided by the present invention; Figure 5 This is a schematic diagram of a visual chart displaying the number of transponder losses provided by the present invention; Figure 6This is a schematic diagram of the structure of the rail transit data analysis device provided by the present invention; Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0021] Currently, the system's operation and maintenance management mainly relies on manual inspections and the recording of basic data. With the continuous increase in subway lines and the massive number of equipment, manual methods are no longer sufficient to efficiently and comprehensively grasp the operational status and trends of the entire network's signaling equipment. While existing signaling maintenance support systems can collect monitoring data, they lack the ability to deeply mine and intelligently analyze this massive amount of data. Specifically, current technology suffers from the following problems: Data integration difficulties: Data generated by various sub-modules of the signaling system (such as morning / evening times, alarms, transponders, and parking) is often scattered across different systems or databases, lacking unified interfaces and standards, making data integration and correlation analysis difficult; Analytical limitations: Existing analyses largely rely on manual experience and basic statistics, lacking the ability to mine data trends, identify abnormal patterns, and trace potential causes, making it difficult to handle complex scenarios; Insufficient visualization and intuitiveness: Even when visualization is available, it is mostly general charts, lacking intelligent descriptions and feature extraction deeply integrated with specific business scenarios, resulting in low efficiency for user understanding and rapid decision-making; Weak prediction and early warning capabilities: Insufficient ability to predict potential system risks and future trends, making it difficult to achieve a shift from passive response to proactive prevention, and failing to fully leverage the value of massive amounts of data.

[0022] Based on this, embodiments of the present invention provide a method, apparatus, device, and storage medium for rail transit data analysis, which can solve the above-mentioned technical problems.

[0023] It should be noted that the executing entity in the embodiments of the present invention may be a rail transit data analysis device, an electronic device, or other devices or equipment, and no specific limitation is made here. The following embodiments will use an electronic device as an example for illustration.

[0024] Figure 1 This is one of the flowcharts illustrating the rail transit data analysis method provided by the present invention, such as... Figure 1 As shown, the method includes the following steps: Step 102: Based on the industry standards and procurement information of rail transit, determine at least one key indicator that needs to be collected in each signaling system of rail transit; the aforementioned signaling system includes the signaling systems of each rail transit line and / or each station, and the aforementioned key indicator is used to characterize the operating status of rail transit.

[0025] The rail transit system may include various lines and stations. Each line includes multiple stations, and each station may include one or more signaling systems or their sub-modules, turnout equipment, etc. These signaling systems and their sub-modules, turnout equipment, etc., are used to generate or collect operating data of trains and / or rail transit equipment.

[0026] Industry standards for rail transit can be standards for relevant data indicators set within the rail transit industry, such as the types of data indicators for train operation as defined in the industry. Procurement information can be related to signaling systems procured within the rail transit industry, such as the type of signaling system and the types of data indicators that can be collected by the system. By taking the intersection or union of the data indicators from both the industry standards and the procurement information, at least one key indicator can be obtained. These key indicators represent the critical data to be collected in each signaling system.

[0027] The key indicators identified above are generally data indicators that can characterize the operation status of rail transit. Optionally, key indicators may include at least one of the following: train arrival time, train delay time, false alarm rate, false alarm rate, train stopping accuracy, and transponder loss count.

[0028] Train arrival and departure times can be combined into a single "train arrival / delay time," which primarily reflects whether a train arrives at its scheduled time. Specifically, it can be obtained by calculating the difference between the actual arrival time and the scheduled arrival time (the duration of arrival / delay). For example, train arrival time (also called train arrival duration) and train departure time (also called train delay duration) can be calculated using the following formula: Early arrival time (ΔT early) = Scheduled arrival time - Actual arrival time; Delay duration (ΔT late) = Actual arrival time - Scheduled arrival time; Among them, early arrival time reflects the time by which the actual arrival time of the train is earlier than the scheduled arrival time, while late arrival time reflects the time by which the actual arrival time of the train is later than the scheduled arrival time.

[0029] The false alarm rate is the ratio of the number of false alarms to the total number of alarms; the false alarm rate is the ratio of the number of manually entered alarms that were not triggered by the system to the total number of alarms.

[0030] Train stopping accuracy reflects the deviation between the actual stopping position and the planned stopping position. The formula for calculating the stopping deviation is: Stopping Deviation (cm) = Actual Stopping Position - Planned Stopping Position. Train stopping accuracy can be obtained directly by comparing a single stopping deviation with a preset stopping deviation range, or by comparing multiple stopping deviations with the preset stopping deviation range and then performing statistical analysis. The preset stopping deviation range includes different stopping deviation ranges and the corresponding quantitative value (i.e., quantitative score) of stopping accuracy for each range.

[0031] The transponder loss count reflects the transponder loss situation, which can be obtained by counting the number of transponder losses within a set time period.

[0032] Step 104: Based on the key indicators, collect the initial operating data corresponding to the key indicators in each signal system through the specified system interface, and store all the initial operating data in a preset database.

[0033] In this step, after determining the multiple key indicators for which data needs to be collected, since the data for each key indicator is scattered across different signaling systems and turnout equipment, this embodiment collects the initial operational data corresponding to each key indicator from each signaling system and turnout equipment through a specified system interface to facilitate the collection of key indicator data generated by all signaling systems and turnout equipment. The specified system interface could be, for example, an ATS (Automatic Train Supervision) interface, an alarm log interface, etc. It is understood that the specified system interface can access all signaling systems and turnout equipment and collect the required data from them. The aforementioned initial operational data can include real-time operational data and historical operational data, meaning that the entire lifecycle data of train operation on the line can be analyzed.

[0034] After obtaining the initial operational data corresponding to each key indicator, the initial operational data can be directly stored in a preset database, or it can be preprocessed before being stored in the preset database. Preprocessing can include data cleaning, noise reduction, format standardization, and missing value imputation. Preprocessing the initial operational data ensures its accuracy and usability. Furthermore, the type of preset database can be set according to actual needs; for example, it could be an SQL (Structured Query Language) database.

[0035] Step 106: Based on the relevant analysis information of the key indicator to be analyzed input by the user, retrieve the data to be analyzed corresponding to the key indicator to be analyzed from the preset database, and analyze the data to be analyzed based on the relevant analysis information to obtain the analysis results corresponding to the key indicator to be analyzed; the relevant analysis information includes data analysis dimensions, and the analysis results include the change trend and anomalies of the key indicator to be analyzed under the data analysis dimensions.

[0036] In this step, after storing the key indicators collected from various signal systems and turnout equipment into a preset database, the data from different systems can be centralized together, enabling rapid data analysis of the stored operational data.

[0037] When a user needs to analyze data in a preset database, the user can first input the key indicators to be analyzed and their related analysis information. There can be one or more key indicators to be analyzed, all of which can be recorded as key indicators to be analyzed. The related analysis information can reflect the relevant information for analyzing the key indicator to be analyzed, such as data analysis dimensions, data analysis time range, and analysis result display type.

[0038] Optionally, the key indicators to be analyzed include at least one of the following: train arrival time, train delay time, false alarm rate, false alarm rate, train stopping accuracy, and transponder loss count.

[0039] After obtaining the key indicator to be analyzed and its related analysis information input by the user, the system can retrieve the corresponding operational data from a pre-set database. Based on the relevant analysis information, the system can then find the operational data to be analyzed (e.g., operational data within the specified time range), which is recorded as the data to be analyzed for that key indicator. Next, the system performs in-depth analysis on this data to obtain the analysis results for that key indicator. These results can include the trend of change and outliers corresponding to the key indicator under the data analysis dimension. The trend refers to the change trend of the key indicator over different time periods, and outliers refer to specific abnormal information when the key indicator exhibits abnormal behavior, such as identifying poorly performing trains, stations, or transponders based on statistical rankings or thresholds.

[0040] Furthermore, the analysis of each key indicator mentioned above can also include statistics on the total number of occurrences, average value, and percentage of outliers during a set period. The trend of change can be the trend of the key indicator in different time periods, or the trend of increase or decrease of outliers.

[0041] For example, the data to be analyzed can be analyzed in depth according to the data analysis dimensions in the relevant analysis information. For instance, by line dimension and the key indicator to be analyzed is the train arrival and departure times, the number of arrival and departure times of the same line in different time periods and the distribution of arrival and departure times can be analyzed. Then, by analyzing the number of arrival and departure times of the line in different time periods, the changing trend of the number of arrival and departure times of the line in different time periods can be obtained. At the same time, the number of arrival and departure times can be compared with a threshold. When the threshold is exceeded, the number of arrival and departure times of the line is regarded as an anomaly corresponding to the key indicator to be analyzed, and the analysis results corresponding to the key indicator of train arrival and departure times can be obtained.

[0042] In this embodiment, based on industry standards and procurement information for rail transit, at least one key indicator for which data needs to be collected in each signaling system of the rail transit system is determined. Based on the key indicator, initial operational data corresponding to the key indicator is collected in each signaling system through a designated system interface, and all initial operational data are uniformly stored in a preset database. According to the relevant analysis information of the key indicator to be analyzed input by the user, the data to be analyzed corresponding to the key indicator to be analyzed is retrieved from the preset database, and the data to be analyzed is analyzed according to the relevant analysis information to obtain the analysis results corresponding to the key indicator to be analyzed. The signaling system includes the signaling systems of each rail transit line and / or each station. The key indicator is used to characterize the operating status of the rail transit system. The relevant analysis information includes data analysis dimensions, and the analysis results include the changing trends and anomalies corresponding to the key indicator to be analyzed under the data analysis dimensions. This method integrates data from different signal systems into a single database via a designated system interface, facilitating subsequent correlation analysis of all signal system data and enhancing the depth of data analysis. Furthermore, by identifying key indicators before collecting and storing corresponding data, the collected data becomes more targeted, leading to more accurate analysis results. Finally, analyzing key indicator data across different data analysis dimensions further enhances the depth of data analysis and the accuracy of the obtained results.

[0043] The following examples illustrate the specific implementation process of analyzing the data to be analyzed based on relevant analytical information.

[0044] In one embodiment, step 106 above, which involves analyzing the data to be analyzed based on relevant analytical information to obtain the analytical results corresponding to the key indicators to be analyzed, may include the following steps: Based on the data to be analyzed, calculate the key indicator data corresponding to the key indicators to be analyzed. Based on the data analysis dimensions in the relevant analysis information, statistical analysis is performed on the key indicator data to determine the changing trends and anomalies of the key indicators to be analyzed under the data analysis dimensions. Based on the changing trends and outliers of the key indicators to be analyzed under the data analysis dimension, the analysis results corresponding to the key indicators to be analyzed are determined.

[0045] As mentioned above, the key indicators to be analyzed may include train arrival time, train delay time, false alarm rate, false alarm rate, train stopping accuracy, and transponder loss count. Train arrival time and train delay time can be collectively referred to as train arrival / delay time. The specific analysis process for these key indicators is explained below.

[0046] The analysis process for the data to be analyzed regarding the key indicator of train arrival and departure times is as follows: The data to be analyzed for train arrival and departure times include the actual arrival time and the scheduled arrival time, which can be obtained through the ATS system.

[0047] After obtaining the data to be analyzed regarding train arrival and departure times, which includes the actual arrival time and planned arrival time of trains at various stations on multiple lines, the duration of arrival and departure for each train at each station can be calculated. The specific calculation method can be: early arrival time = planned arrival time - actual arrival time; late arrival time = actual arrival time - planned arrival time.

[0048] After calculating the morning and evening arrival times for each train at each station, the number of early arrivals and late arrivals can be counted separately, i.e., the number of early arrivals with a non-zero arrival time and the number of late arrivals with a non-zero arrival time. Simultaneously, the percentage of trains arriving on time can be calculated to obtain the train punctuality rate. The morning and evening arrival times, the number of early and late arrivals, and the punctuality rate can then be used as key indicators of train arrival and departure times.

[0049] Then, based on the user-input / configured relevant analysis information, key indicator data on train arrival and departure times can be analyzed. This relevant analysis information can include data analysis dimensions, analysis objectives (e.g., specifically analyzing early arrival, late arrival, or both), and analysis time range. The analysis objective refers to the user's selection of "early arrival" and / or "late arrival" for statistical analysis. Data analysis dimensions include: route dimension, station dimension, and train dimension. Multiple dimensions can be selected, meaning multiple routes, stations, or trains can be analyzed simultaneously. Optionally, up to seven routes, stations, or trains can be selected simultaneously. The analysis time range can include daily, monthly, and annual time ranges, all of which can be configured and input by the user. For example, if the analysis time range is daily, the user can select a specific date to display the statistical values ​​of each hour throughout the day, and can also select a specific time of day to generate a static chart. Similarly, if the analysis time range is monthly, the user can select a specific month to display the statistical values ​​of each day of the month; if a month including the current day is selected, the cutoff date is that day, generating a static chart. Likewise, if the analysis time range is annual, the user can select a specific year to display the statistical values ​​of each month throughout the year; if a year including the current day is selected, the cutoff month is that month and day, generating a static chart.

[0050] By having users pre-input the data analysis dimensions and analysis time range (or leaving them blank, the default is to analyze all historical times prior to the current moment), the system can then analyze key indicator data of train arrival / departure times according to the data analysis dimensions and / or analysis time range, obtaining analysis results under specific data analysis dimensions. Specifically, initial analysis results can be obtained under the three data analysis dimensions mentioned above, including: 1. The analysis results at the route level include: the number of early morning and late evening departures and the duration distribution of early morning and late evening departures for the same route at different times.

[0051] 2. The analysis results at the station level include: the number of early morning and late evening departures and the duration distribution of early morning and late evening departures at the same station at different times.

[0052] 3. The analysis results under the train dimension include: the number of early morning and late departures of the same train at different stations and at different times, as well as the distribution of the duration of early morning and late departures.

[0053] The initial analysis of the same train route's morning and evening departure times and their durations reveals trends in both. By comparing these figures with thresholds, periods exceeding the threshold can be identified as outliers. Finally, the trends in morning and evening departure times and durations, along with other outliers, constitute the final analysis results for the key indicator of train departure times.

[0054] II. The false alarm rate and false negative rate of the above alarms can also be used together as a key indicator. The analysis process for the data to be analyzed for the key indicator of false alarm rate and false negative rate is as follows: The data to be analyzed, corresponding to the false alarm rate and missed alarm rate, includes real-time and historical alarm lists. These lists contain alarm categories (maintenance alarms, false alarms, and real alarms) and manual judgment results. In other words, through this list, we can obtain alarms triggered by the system, alarms manually entered but not triggered by the system, and alarms judged as false alarms by manual judgment.

[0055] After obtaining the data to be analyzed corresponding to the false alarm rate and false negative rate, the total number of alarms can be obtained by counting all alarms in the list. Simultaneously, the number of manually entered alarms that were not triggered by the system can be obtained by counting those manually entered but not triggered, and the number of false alarms can be obtained by counting those manually determined to be false alarms. The false alarm rate and false negative rate can then be calculated using the following formulas: False alarm rate = Number of false alarms / Total number of alarms; The false alarm rate = the number of alarms manually entered but not triggered by the system / the total number of alarms.

[0056] Then, the false alarm rate and false negative rate are used as key indicator data corresponding to the critical indicators of alarm false alarm rate and false negative rate. Subsequently, the key indicator data can be analyzed based on relevant analysis information input / configured by the user. This relevant analysis information can include data analysis dimensions, analysis objectives (such as specifically analyzing false alarm rate, false negative rate, and false alarm rate), and analysis time range. The analysis objective refers to the user's selection of "false alarm rate" and / or "false negative rate" for statistical analysis. The analysis time range can include daily, monthly, and annual time ranges, all of which can be configured and input by the user. Data analysis dimensions can include lines, stations / trains, and subsystems (such as signaling systems).

[0057] For example, when analyzing data based on the line, one can choose the full line dimension or the full network dimension. Then, among the key indicator data mentioned above, one can select the key indicator data for the current year, the current month, or the entire history (since the system went live) for analysis. For instance, if one chooses the current year as the data analysis dimension, one can statistically analyze and obtain all alarm counts for the entire line from January 1st of this year to the present. Then, the number of false alarms in this year can be compared with the total number of alarms in this year to obtain the false alarm rate for this year. At the same time, the number of manually entered alarms that were not triggered by the system in this year can be compared with the total number of alarms in this year to obtain the missed alarm rate for this year. If one chooses the current month as the data analysis dimension, one can statistically analyze and obtain the data for this month. The system calculates the false alarm rate by comparing the number of false alarms recorded this month to the total number of alarms recorded this month, and the missed alarm rate by comparing the number of manually entered alarms that were not triggered by the system to the total number of alarms recorded this month. Alternatively, by selecting the entire historical data as the data analysis dimension, the system can statistically analyze the total number of alarms recorded since its launch. The system then calculates the false alarm rate since its launch by comparing the number of false alarms recorded since its launch to the total number of alarms recorded since its launch, and the missed alarm rate by comparing the number of manually entered alarms that were not triggered by the system to the total number of alarms recorded since its launch.

[0058] For example, if a user selects a specific data analysis dimension for a particular network line and the analysis timeframe is the entire historical timeframe, then the false alarm rate and missed alarm rate for that line in each month and year can be statistically obtained using the method described above. Then, by sorting the false alarm rate and missed alarm rate for each line by month, the changing trends of the false alarm rate and missed alarm rate over time can be obtained. Simultaneously, the false alarm rate and missed alarm rate for each month of the line can be compared with their respective thresholds. False alarm rates exceeding the thresholds and their corresponding months, as well as missed alarm rates exceeding the thresholds and their corresponding months, can be identified as anomalies for that line. Finally, the changing trends of the line's false alarm rate and missed alarm rate across different months, along with anomalies, are used as the final analysis results for the key indicators of false alarm rate and missed alarm rate.

[0059] III. The analysis process for the data to be analyzed, which is a key indicator of train stopping accuracy, is as follows: Based on the data to be analyzed corresponding to the train stopping accuracy, calculate the stopping deviation of each train; Based on the stopping deviation of each train, determine the corresponding quantitative value of stopping accuracy for each train; The evaluation quantification value for each train is determined based on the quantitative values ​​of each stopping accuracy within a set time range and the number of times each stopping accuracy quantification value occurs. Based on the evaluation quantification value of each train, the analysis results corresponding to the train stopping accuracy are determined.

[0060] The data to be analyzed for train stopping accuracy includes: stopping position records during train operation (such as actual stopping position and planned stopping position), train driving mode (including automatic driving mode and manual driving mode), etc.

[0061] After obtaining the data to be analyzed, the parking deviation can be obtained by calculating the difference between the actual parking position and the planned parking position of each train at each stop. The specific formula is: Parking Deviation (cm) = Actual Parking Position - Planned Parking Position. Then, the parking deviation of each train at each stop, as well as the train driving mode of each train at each trip, are used as key indicator data corresponding to the key indicator of parking accuracy.

[0062] Then, key indicator data can be analyzed based on user-inputted / configured relevant analysis information. This information can include data analysis dimensions, analysis objectives (e.g., uplink, downlink, or both), and analysis time range. The analysis objective refers to the user's selection of "uplink" and / or "downlink" for each station / station for statistical analysis. The analysis time range can include daily, weekly (last seven days), and monthly (this month or last month) time ranges, all of which can be configured and input by the user. Data analysis dimensions can include train dimensions, station / station dimensions, etc.

[0063] When performing data analysis, users can select / input the route (single selection), analysis time range, train number (multiple selection / all selection), and stations (multiple selection / all selection, including up and down lines), and then perform the following analysis and calculations: 1. Total number of parking times: Distinguish between autonomous driving mode and manual driving mode, that is, count the total number of parking times in autonomous driving mode and the total number of parking times in manual driving mode within the analysis time range.

[0064] 2. Parking accuracy / deviation distribution statistics: The number of times is counted according to the parking deviation range (e.g., greater than 50, 30~50, 15~30, 10~15, 5~10, -5~5, -5~-10, -10~-15, -15~-30, -30~-50, less than -50, unit: cm). That is, each parking deviation is compared with multiple parking deviation ranges to determine the number of times the parking falls within each parking deviation range.

[0065] 3. Statistics on the number of times parking is abnormal: Count the number of times the absolute value of the parking deviation is greater than the threshold (e.g., 50cm).

[0066] 4. Evaluation Score Calculation: Based on the parking deviation range, assign values ​​(e.g., -5~5cm equals 100 points), statistically evaluate the train / station stopping data and take the average score. The specific calculation formula is as follows: ; Among them, the score i Indicates the first i A quantitative value for parking accuracy (obtained through the correspondence between parking deviation range and score, e.g., -5~5cm equals 100 points), number of times. i Indicates the first i The number of times the parking accuracy quantification value appears, the evaluation quantification value is the evaluation score, which represents the overall evaluation quantification value of the train / station during this statistical process (i.e., within the analysis time range set above).

[0067] 5. Parking Deviation Count Statistics: List the number of parking times within each parking deviation range.

[0068] The above process can be used to calculate the statistical range of parking deviation distribution for any train / station within the set analysis time range, the number of stops where the absolute value of parking deviation is greater than the threshold, and the overall quantitative evaluation value of the train / station. Among them, the number of stops where the absolute value of parking deviation is greater than the threshold can be regarded as an anomaly. The above three types of data can be used as the analysis results corresponding to the key indicator of parking accuracy.

[0069] IV. The analysis process for the data to be analyzed, which is a key indicator of the number of transponder losses, is as follows: The data to be analyzed corresponding to the number of transponder losses includes: transponder reading data recorded by the train onboard unit (TCU) (including loss records), transponder number information, etc.

[0070] After obtaining the data to be analyzed, the number of transponders lost can be obtained from the loss records. Then, the number of transponders lost and their number signals are used as key indicator data corresponding to the key indicator of the number of transponders lost.

[0071] Then, key indicator data can be analyzed based on user-inputted / configured relevant analysis information. This relevant analysis information may include data analysis dimensions, analysis time range, transponder number, etc. The analysis time range can include daily, weekly (last seven days), monthly (this month or last month), etc., all of which can be configured and input by the user. Data analysis dimensions may include train dimensions, transponder dimensions, etc.

[0072] When performing data analysis, users can select / input the route (single choice), analysis time range, train group number (multiple choice), transponder number (multiple choice, supports fuzzy search), etc., and then perform the following analysis and calculations: 1. Transponder Loss Statistics: Count the number of times each train or each transponder is lost within the set analysis time range.

[0073] 2. TCI / TC2 terminal loss count statistics (for trains).

[0074] 3. Ranking logic: Arranged from top to bottom according to the number of transponder loss.

[0075] The above method allows us to obtain the number of transponder losses for each train or transponder in each time period within the analysis timeframe, thus revealing the trend of transponder loss counts for each train or transponder within the analysis timeframe. Simultaneously, the number of transponder losses for each train or transponder in each time period within the analysis timeframe can be compared with a loss threshold to identify transponder loss counts exceeding the threshold and their corresponding times, as outliers. The trend of transponder loss counts for each train or transponder within the analysis timeframe and the outliers are then used as the analysis results for the key indicator of transponder loss counts.

[0076] In this embodiment, key indicator data is first calculated based on the data to be analyzed for different key indicators. Then, statistical analysis is performed according to the data analysis dimensions to obtain the trend and outliers of the indicator data, thereby obtaining the analysis results of the indicators. This progressive processing method allows for in-depth processing of the indicator data, improving the strength and accuracy of the data analysis. Furthermore, for the parking accuracy indicator, parking deviation can be calculated, and then the parking accuracy quantification value can be calculated. Finally, the evaluation quantification value for each vehicle can be calculated to obtain the parking accuracy analysis results. This refines the analysis process for the parking accuracy indicator and improves the accuracy of the data analysis for this indicator.

[0077] The following examples illustrate the process of visualizing the analysis results.

[0078] In one embodiment, the above method further includes the following steps: Based on the type of the key indicator to be analyzed, determine at least one target visualization chart type corresponding to the key indicator to be analyzed; The analysis results corresponding to the key indicators to be analyzed are transformed into visualization charts of the target visualization chart type and then displayed.

[0079] The types of visualization charts include bar charts, line charts, curve charts, tables, lists, etc. Different key indicators correspond to different types of visualization charts. The target visualization chart type corresponding to each key indicator can be preset. After obtaining the type of the key indicator to be analyzed, one or more target visualization chart types corresponding to the key indicator to be analyzed can be obtained.

[0080] For the key indicator of train arrival and departure times, the corresponding target visualization chart type can be a bar chart or a line chart, for example, see Figure 2 The diagram shows a visualization of train arrival and departure times. It can generate a bar chart for each line / station / train on a time unit scale, displaying different percentages of arrival and departure times, such as within 2 minutes, 2-5 minutes, and more than 5 minutes. It can also display data such as the on-time rate trend over time through line charts, including the on-time rate trend under different driving modes and the overall on-time rate. Furthermore, it can display corresponding bar charts for different driving modes, using different colored bars to represent different driving modes. Additionally, it provides interactive functionality; hovering the mouse over the displayed bar charts displays information such as the line / station / train name, total number of arrival and departure times, percentage, and quantity.

[0081] For the key metrics of false alarm rate and false negative rate, the corresponding target visualization chart type can be a line chart, for example, see Figure 3 The diagram shows a visualization of the false alarm rate and the missed alarm rate. Two continuous line graphs are generated, one for the number of false alarms (manually entered but not triggered by the system) and the other for the number of missed alarms (manually entered but not triggered by the system). The horizontal axis of the line graphs represents time, and the vertical axis represents the number of false alarms. An interactive function is also provided, displaying specific values ​​at the mouse hover position on the line graphs.

[0082] For the key indicator of parking accuracy, the corresponding target visualization chart type can be a bar chart, line chart, or list. See, for example... Figure 4 The diagram shows a visualization of parking accuracy, including a bar chart displaying the distribution of parking accuracy / deviation and the top 10 rankings of the quantitative evaluation values. The line chart shows the trend of cumulative parking deviation.

[0083] Specifically, bar charts and line graphs can display: total number of stops, parking accuracy distribution, trend of abnormal parking times in autonomous / manual driving modes, ranking of the worst parking accuracy, and TOP 10 analysis (train group number / station, evaluation score, number of stops). Additionally, interactive functions are provided, allowing users to check the boxes to show / hide the legend on the displayed bar charts and line graphs, and to display specific values ​​when the mouse hovers over them. The above list can be a detailed list, displaying: sequence number, occurrence time, route, train group number, station, up / down direction, driving mode, and parking deviation (cm); filtering criteria include: time, route (unique value), train group number (dynamically loaded after route selection), station (dynamically loaded after route selection, supports fuzzy search), and parking deviation. Furthermore, interactive functions are provided, such as clicking the "Search" button to refresh the list, selecting a route before selecting the train group number / station, and filtering by station only.

[0084] For the key metric of transponder loss count, the corresponding target visualization chart type can be a line graph, table, or list. See, for example... Figure 5 The visualization of transponder loss counts is shown below. The graphs include: a train / transponder loss trend graph (horizontal axis: time, vertical axis: number), specifically displaying the number of transponder losses at different time periods on the train side, and the number of losses for different transponders at different time periods on the transponder side. The table can be a TOP 5 loss statistics ranking table (including serial number, line, trainset / transponder number, number of losses, TCI / TC2 end losses, etc.). Interactive functions are also provided, including legend highlighting and a "View More" button to pop up the complete ranking list. The list can be a detailed list, displaying: serial number, occurrence time, line, trainset number, TC1 / TC2, transponder name, driving mode, corresponding axle counting section, transponder's concentration area, and kilometer marker. Filtering criteria include: time, line (unique value), trainset number (dynamically loaded after line selection), and transponder number (dynamically loaded after line selection, supports fuzzy search). In addition, interactive features are provided, such as clicking the "Search" button to refresh the list, and the list sorting changes according to the filter criteria (only lines or including train numbers / transponders).

[0085] Understandably, each key indicator visualization should include a detailed data list for viewing raw or aggregated data records. The header content varies depending on the specific analysis, but typically includes basic information such as time, route, train number, and station. A sorted list can also be provided: the list data can be sorted chronologically or according to the ranking of the statistical objects.

[0086] It should be noted that the above Figures 2-5This is merely a visual example; the specific numerical values ​​within it do not affect the essence of the technical solution of this invention.

[0087] In this embodiment, the analysis results of key indicators are displayed using corresponding visual charts. This intuitive and diverse visualization allows users to quickly identify the current status, evolution patterns, and prominent issues of key indicators, enhancing the comprehensibility of information. Furthermore, by deeply integrating the charts with specific business scenarios, it facilitates users' understanding of the analysis results and improves the efficiency of users' decision-making based on the visual analysis results.

[0088] The following examples illustrate the intelligent solutions provided based on the above analysis results.

[0089] In one embodiment, the above method further includes the following steps: Based on the changing trends and anomalies of the key indicators to be analyzed in the data analysis dimension, as well as the various fault modes of the signal system in rail transit, determine the reasons for the anomalies of the key indicators to be analyzed. Based on the reasons for the abnormality of the key indicator to be analyzed, determine and output the solution to restore the key indicator to normal.

[0090] As mentioned above, the analysis results for each key indicator can include trends and anomalies within its data analysis dimension, such as the longest delays, high false alarm rates, large parking accuracy deviations, and frequent transponder loss. Based on the trends and anomalies of each key indicator within its data analysis dimension, along with the original data to be analyzed, and by using various fault modes corresponding to the signaling system in rail transit, such as braking system failures, signaling system installation failures, and driver operation failures, and combining industry experience and system data for correlation analysis, the causes of anomalies in each key indicator can be predicted. Examples of causes include: brake system wear, beacon installation misalignment, antenna sensitivity issues, and improper driver operation.

[0091] Then, by establishing the correspondence between causes and solutions, or by training a network model with fault causes and solutions, we can obtain the solutions corresponding to the causes of the current key indicators' anomalies. These solutions are used to restore the data of the corresponding key indicators to normal, and may include maintenance, repair, optimization, or training recommendations.

[0092] For different key indicators, such as train arrival / delay times, we can analyze the main causes of delays (e.g., line capacity, signal delays, train operation organization, etc.) and obtain corresponding solutions, such as suggesting optimization of train schedules. For false alarms / missed alarms, we can analyze the causes of alarms and obtain corresponding solutions, such as suggesting optimization of alarm thresholds, sensor parameters, or inspection and maintenance procedures. For parking accuracy, we can analyze the factors leading to large parking deviations and obtain corresponding solutions, such as suggesting inspection and maintenance of vehicle equipment or the track environment. For transponder loss, we can analyze the reasons for transponder reading failures and obtain corresponding solutions, such as suggesting inspection of the transponder itself, the onboard antenna, or the transmission link.

[0093] Furthermore, a summary description of the overall situation, trends, and outliers / anomalies of the aforementioned statistical data can be provided and displayed at designated locations on the visualization charts of the corresponding key indicators. Simultaneously, the solutions corresponding to each key indicator can be presented / output as text boxes at designated locations on the visualization charts, clearly indicating the problematic trains / stations / transponders and corresponding improvement measures.

[0094] In addition, it should be noted that all analysis modules within the rail transit system possess the aforementioned analysis functions, enabling intelligent interpretation of data and guidance for operation and maintenance.

[0095] Alternatively, a structured analysis report can be generated and saved based on the analysis results, visualizations, and solutions for each key indicator. This allows for the generation and saving of a structured analysis report for each key indicator, integrating statistical data, visualizations, and intelligent text summaries to form a structured and easily accessible analysis report. This provides signal professionals with effective operational awareness, problem diagnosis, and improvement suggestions, supporting refined management and scientific decision-making.

[0096] In this embodiment, the reasons for the anomalies in key indicators are determined by analyzing the changing trends and anomalies of key indicators under the corresponding data analysis dimensions, combined with various system failure modes. Solutions to restore them to normal are then provided and output in text form. This allows for targeted maintenance suggestions based on the analysis results, guiding actual operation and maintenance work, and also makes it convenient for users to view the corresponding solutions in a timely manner.

[0097] As described in the above embodiments, the system corresponding to the rail transit data analysis method of this invention has multi-dimensional and comprehensive analysis capabilities. It can perform unified and in-depth analysis of multiple key signal indicators such as arrival / delay, false alarms / missed alarms, parking accuracy, and transponder loss. Simultaneously, it can perform intelligent data description and trend summarization, providing not only data statistics but also automatically generating textual descriptions and trend summaries of data characteristics, extracting insights such as "Train XX performed poorly, possibly related to XX reason." Furthermore, it can provide refined hierarchical display and interaction, supporting data filtering, comparison, and viewing by multiple dimensions such as line, station, train number, and transponder, and presenting data in various forms such as charts and lists, providing rich interactive functions. Finally, it can provide quantitative evaluation and maintenance suggestions, quantitatively evaluating key indicators such as parking accuracy (e.g., evaluation scores) and providing targeted maintenance suggestions based on the analysis results to guide actual operation and maintenance work.

[0098] The above technical solution can achieve the following technical effects: 1. Improve operational efficiency: Through automated data analysis, visualization, and intelligent diagnostic suggestions, significantly reduce manual analysis time and improve the efficiency of troubleshooting and operational decision-making.

[0099] 2. Strengthen early warning and prevention capabilities: accurately identify potential risk points (such as trains / stations with poor stopping accuracy, transponders that are easily lost), change from passive response to proactive prevention, and reduce failure rate.

[0100] 3. Optimize operational performance: Through in-depth analysis of train arrival and departure times and stopping accuracy, data support is provided to improve the punctuality rate and service quality of train operations.

[0101] 4. Scientific Decision Support: Provides managers with intuitive and comprehensive operational data views and professional analytical insights to assist in scientific management and optimal resource allocation.

[0102] 5. Maximize data value: Transform scattered operational data into valuable analytical information and actionable improvement suggestions, fully tapping the potential of massive amounts of data.

[0103] The rail transit data analysis device provided by the present invention is described below. The rail transit data analysis device described below and the rail transit data analysis method described above can be referred to in correspondence.

[0104] Figure 6 This is a schematic diagram of the structure of the rail transit data analysis device provided by the present invention. (See attached diagram) Figure 6 As shown, the device may include: The indicator determination module 610 is used to determine at least one key indicator that needs to be collected in each signaling system of the rail transit system, based on the industry standards and procurement information of the rail transit system; the signaling system includes the signaling system of each line and / or each station of the rail transit system, and the key indicator is used to characterize the operation status of the rail transit system. The data acquisition module 620 is used to collect the initial operating data corresponding to the key indicators in each signal system through the specified system interface, and to store the initial operating data in a preset database. The data analysis module 630 is used to retrieve the data to be analyzed corresponding to the key indicator to be analyzed from a preset database based on the relevant analysis information of the key indicator to be analyzed input by the user, and to analyze the data to be analyzed based on the relevant analysis information to obtain the analysis results corresponding to the key indicator to be analyzed; the relevant analysis information includes data analysis dimensions, and the analysis results include the change trend and anomalies of the key indicator to be analyzed under the data analysis dimensions.

[0105] In one embodiment, the data analysis module 630 is specifically used to calculate the key indicator data corresponding to the key indicator to be analyzed based on the data to be analyzed; perform statistical analysis on the key indicator data according to the data analysis dimensions in the relevant analysis information to determine the changing trend and anomalies corresponding to the key indicator to be analyzed under the data analysis dimensions; and determine the analysis results corresponding to the key indicator to be analyzed based on the changing trend and anomalies corresponding to the key indicator to be analyzed under the data analysis dimensions.

[0106] In one embodiment, the above-mentioned apparatus further includes: The visualization module is used to determine at least one target visualization chart type corresponding to the key indicator to be analyzed, based on the type of key indicator to be analyzed; to convert the analysis results corresponding to the key indicator to be analyzed into a visualization chart of the target visualization chart type, and to display the visualization chart.

[0107] In one embodiment, the above-mentioned apparatus further includes: The decision module is used to determine the cause of the anomalies in the key indicators to be analyzed based on the changing trends and anomalies of the key indicators under the data analysis dimension, as well as the various fault modes corresponding to the signal system in rail transit; based on the cause of the anomalies in the key indicators to be analyzed, it determines and outputs the solution to restore the key indicators to normal.

[0108] In one embodiment, the above-mentioned apparatus further includes: The report generation module is used to generate and save structured analysis reports corresponding to the key indicators to be analyzed, based on the analysis results, visualization charts, and solutions.

[0109] In one embodiment, the key indicator to be analyzed includes at least one of the following: Train arrival time, train delay time, false alarm rate, false alarm rate, train stopping accuracy, and transponder loss count.

[0110] In one embodiment, when the key indicators to be analyzed include train stopping accuracy, the data analysis module 630 is specifically used to calculate the stopping deviation of each train based on the data to be analyzed corresponding to the train stopping accuracy; determine the stopping accuracy quantification value corresponding to each train based on the stopping deviation of each train; determine the evaluation quantification value corresponding to each train based on the stopping accuracy quantification values ​​of each train within a set time range and the number of times each stopping accuracy quantification value appears; and determine the analysis result corresponding to the train stopping accuracy based on the evaluation quantification value of each train.

[0111] It should be noted that the apparatus provided in this embodiment of the invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0112] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include: a processor 710, a communications interface 720, a memory 730, and a communications bus 740, wherein the processor 710, the communications interface 720, and the memory 730 communicate with each other through the communications bus 740. The processor 710 can call logic instructions in the memory 730 to execute a rail transit data analysis method. This method includes: determining at least one key indicator for which data needs to be collected in each signaling system of the rail transit system, based on industry standards and procurement information; the signaling systems include the signaling systems of each rail transit line and / or each station, and the key indicator is used to characterize the operating status of the rail transit system; collecting initial operating data corresponding to the key indicator in each signaling system through a specified system interface, and storing all initial operating data in a preset database; obtaining the data to be analyzed corresponding to the key indicator from the preset database based on relevant analysis information input by the user, and analyzing the data to be analyzed based on the relevant analysis information to obtain the analysis results corresponding to the key indicator to be analyzed; the relevant analysis information includes data analysis dimensions, and the analysis results include the changing trends and anomalies corresponding to the key indicator to be analyzed under the data analysis dimensions.

[0113] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0114] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the rail transit data analysis method provided by the above methods. The method includes: determining at least one key indicator that needs to be collected in each signaling system of the rail transit according to industry standards and procurement information; the signaling system includes the signaling systems of each rail transit line and / or each station, and the key indicator is used to characterize the operation status of the rail transit; collecting initial operating data corresponding to the key indicator in each signaling system through a specified system interface according to the key indicator, and storing each initial operating data in a preset database; obtaining the data to be analyzed corresponding to the key indicator to be analyzed from the preset database according to the relevant analysis information input by the user, and analyzing the data to be analyzed according to the relevant analysis information to obtain the analysis result corresponding to the key indicator to be analyzed; the relevant analysis information includes data analysis dimensions, and the analysis result includes the change trend and anomalies corresponding to the key indicator to be analyzed under the data analysis dimensions.

[0115] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program is implemented to perform the rail transit data analysis method provided by the above methods. The method includes: determining at least one key indicator that needs to be collected in each signaling system of the rail transit system according to industry standards and procurement information; the signaling system includes the signaling systems of each rail transit line and / or each station, and the key indicator is used to characterize the operation status of the rail transit system; collecting initial operating data corresponding to the key indicator in each signaling system through a designated system interface according to the key indicator, and storing each initial operating data in a preset database; obtaining the data to be analyzed corresponding to the key indicator to be analyzed from the preset database according to the relevant analysis information input by the user, and analyzing the data to be analyzed according to the relevant analysis information to obtain the analysis result corresponding to the key indicator to be analyzed; the relevant analysis information includes data analysis dimensions, and the analysis result includes the change trend and anomalies corresponding to the key indicator to be analyzed under the data analysis dimensions.

[0116] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0117] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing rail transit data, characterized in that, include: Based on industry standards and procurement information for rail transit, at least one key indicator is determined as to be the data to be collected in each signaling system of the rail transit system; the signaling system includes the signaling systems of each line and / or each station of the rail transit system, and the key indicator is used to characterize the operating status of the rail transit system. Based on the key indicators, the initial operating data corresponding to the key indicators are collected in each of the signal systems through the specified system interface, and the initial operating data are uniformly stored in a preset database. Based on the relevant analysis information of the key indicator to be analyzed input by the user, the data to be analyzed corresponding to the key indicator to be analyzed is obtained from the preset database, and the data to be analyzed is analyzed according to the relevant analysis information to obtain the analysis results corresponding to the key indicator to be analyzed; the relevant analysis information includes data analysis dimensions, and the analysis results include the change trend and anomalies of the key indicator to be analyzed under the data analysis dimensions.

2. The rail transit data analysis method according to claim 1, characterized in that, The step of analyzing the data to be analyzed based on the relevant analysis information to obtain the analysis results corresponding to the key indicators to be analyzed includes: Based on the data to be analyzed, calculate the key indicator data corresponding to the key indicator to be analyzed. According to the data analysis dimensions in the relevant analysis information, statistical analysis is performed on the key indicator data to determine the changing trend and anomalies of the key indicator to be analyzed under the data analysis dimensions. Based on the changing trends and outliers of the key indicators to be analyzed under the data analysis dimension, the analysis results corresponding to the key indicators to be analyzed are determined.

3. The rail transit data analysis method according to claim 1, characterized in that, The method further includes: Based on the type of the key indicator to be analyzed, determine at least one target visualization chart type corresponding to the key indicator to be analyzed; The analysis results corresponding to the key indicators to be analyzed are transformed into visualization charts of the target visualization chart type and then displayed.

4. The rail transit data analysis method according to claim 3, characterized in that, The method further includes: Based on the changing trends and anomalies of the key indicators to be analyzed under the data analysis dimension, and the various fault modes corresponding to the signal system in the rail transit, determine the reasons for the anomalies of the key indicators to be analyzed. Based on the reasons for the abnormality of the key indicator to be analyzed, determine and output a solution to restore the key indicator to normal.

5. The rail transit data analysis method according to claim 4, characterized in that, The method further includes: Based on the analysis results, visualization charts, and solutions of the key indicators to be analyzed, a structured analysis report corresponding to the key indicators to be analyzed is generated and saved.

6. The rail transit data analysis method according to any one of claims 1 to 5, characterized in that, The key indicators to be analyzed include at least one of the following: Train arrival time, train delay time, false alarm rate, false alarm rate, train stopping accuracy, and transponder loss count.

7. The rail transit data analysis method according to claim 6, characterized in that, When the key indicator to be analyzed includes train stopping accuracy, the step of analyzing the data to be analyzed based on the relevant analysis information to obtain the analysis results corresponding to the key indicator to be analyzed includes: Based on the data to be analyzed corresponding to the train stopping accuracy, calculate the stopping deviation of each train; Based on the stopping deviation of each train, determine the corresponding quantitative value of stopping accuracy for each train; The evaluation quantification value for each train is determined based on the quantitative values ​​of each stopping accuracy within a set time range and the number of times each stopping accuracy quantification value occurs. Based on the evaluation quantification value of each train, the analysis results corresponding to the train stopping accuracy are determined.

8. A rail transit data analysis device, characterized in that, include: The indicator determination module is used to determine at least one key indicator that needs to be collected in each signaling system of the rail transit system, based on industry standards and procurement information of the rail transit system; the signaling system includes the signaling systems of each line and / or each station of the rail transit system, and the key indicator is used to characterize the operating status of the rail transit system. The data acquisition module is used to collect the initial operating data corresponding to the key indicators in each of the signal systems through a specified system interface, and to store the initial operating data in a preset database. The data analysis module is used to retrieve the data to be analyzed corresponding to the key indicator to be analyzed from the preset database based on the relevant analysis information input by the user, and to analyze the data to be analyzed based on the relevant analysis information to obtain the analysis results corresponding to the key indicator to be analyzed; the relevant analysis information includes data analysis dimensions, and the analysis results include the change trend and anomalies of the key indicator to be analyzed under the data analysis dimensions.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the rail transit data analysis method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the rail transit data analysis method as described in any one of claims 1 to 7.

Images