Index processing method and device of rail transit management system

Abstract

The invention relates to an index processing method and device of a rail transit management system. The method comprises the steps of obtaining a rail transit management index set of multiple index types in response to an index processing request; according to a preset decomposition rule, decomposing each rail transit management index set to obtain an initial management index corresponding to each rail transit subsystem; wherein each initial management index comprises a plurality of initial index values, and each initial index value has a corresponding index type and an initial weight; acquiring real-time rail transit data of each rail transit subsystem, and adjusting each initial index value and each initial weight according to the real-time rail transit data so as to update each initial management index and obtain a target management index; and converting each target management index into a corresponding rail transit control scheduling instruction, and transmitting each rail transit control scheduling instruction to a corresponding rail transit subsystem. By adopting the method, the decision-making efficiency, the real-time performance and the accuracy of rail transit index management can be improved.

Description

Technical Field

[0001] This application relates to the field of rail transit system technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for processing indicators in a rail transit management system. Background Technology

[0002] With the development of technologies such as artificial intelligence, big data, and cloud computing, rail transit management is gradually becoming more intelligent and automated. The rail transit management system centrally manages various rail transit management indicators, decomposes these indicators, and transmits them to various rail transit subsystems (such as passenger station management systems, station management systems, and rail power control systems) for the management of each subsystem.

[0003] In related technologies, the decomposition of rail transit management indicators mainly relies on the experience of management personnel, which is difficult to adapt to complex and ever-changing environments such as peak passenger flow and equipment failure, and is prone to indicator mismatch and response lag. Moreover, after receiving the decomposed rail transit management indicators, the rail transit subsystem still needs relevant personnel to allocate resources and adjust operational decisions, making it difficult to achieve the corresponding rail transit management indicators in a timely manner. Summary of the Invention

[0004] Based on this, it is necessary to provide a rail transit management system indicator processing method, device, computer equipment, computer-readable storage medium, and computer program product that can improve the decision-making efficiency, real-time performance, and accuracy of rail transit indicator management, addressing the aforementioned technical problems.

[0005] Firstly, this application provides a method for processing indicators in a rail transit management system, wherein the rail transit management system communicates with multiple rail transit subsystems, and the method includes:

[0006] In response to indicator processing requests, obtain a set of rail transit management indicators of various indicator types;

[0007] According to the preset decomposition rules, each set of rail transit management indicators is decomposed to obtain the initial management indicators corresponding to each rail transit subsystem; wherein, each initial management indicator includes multiple initial indicator values, and each initial indicator value has a corresponding indicator type and initial weight.

[0008] Real-time rail transit data of each of the rail transit subsystems is obtained, and the initial index values ​​and initial weights of each of the initial indicators are adjusted according to the real-time rail transit data to update the initial management indicators and obtain the target management indicators.

[0009] The target management indicators are converted into corresponding rail transit control scheduling instructions, and the rail transit control scheduling instructions are transmitted to corresponding rail transit subsystems; wherein the rail transit control scheduling instructions are used to achieve the target management indicators by the rail transit subsystems.

[0010] In one of the embodiments, the adjusting of the initial indicator values and the initial weights according to the real-time rail transit data includes:

[0011] adjusting the initial indicator values according to differences between the real-time rail transit data and corresponding preset thresholds;

[0012] determining system states of the rail transit subsystems according to the real-time rail transit data, and determining target weights matched with the system states;

[0013] adjusting the initial weights according to the target weights.

[0014] In one of the embodiments, the adjusting of the initial indicator values according to the differences between the real-time rail transit data and corresponding preset thresholds includes:

[0015] determining a first difference between the real-time rail transit data and a corresponding preset threshold in a case that a current time meets a time corresponding to a preset indicator adjustment period;

[0016] if the first difference does not meet a corresponding preset condition, adjusting the initial indicator value of the corresponding rail transit subsystem according to the first difference;

[0017] in a case that an abnormal event occurs in any of the rail transit subsystems, determining a second difference between real-time rail transit data of the rail transit subsystem in which the abnormal event occurs and a corresponding preset threshold;

[0018] if the second difference does not meet a corresponding preset condition, adjusting the initial indicator value of the rail transit subsystem in which the abnormal event occurs according to the second difference.

[0019] In one of the embodiments, the determining of the system states of the rail transit subsystems according to the real-time rail transit data and the determining of the target weights matched with the system states include:

[0020] inputting the system states into a pre-trained weight allocation reinforcement learning model, mapping the system states into continuous action spaces by the weight allocation reinforcement learning model, and outputting the target weights matched with the system states according to the continuous action spaces.

[0021] In one embodiment, each of the initial indicator values ​​also has a corresponding indicator level, which includes a track line level, a station level, and a job level. The decomposition of each set of rail transit management indicators according to a preset decomposition rule includes:

[0022] According to the preset spatiotemporal dimension decomposition rules, each set of rail transit management indicators is decomposed into the initial indicator values ​​of the rail line level of each rail transit subsystem.

[0023] According to the preset equipment association decomposition rules, the initial index values ​​of each track line level are decomposed into the initial index values ​​of each station level of each rail transit subsystem.

[0024] According to the preset job mapping decomposition rules, the initial index values ​​of each station level are decomposed into the initial index values ​​of each job level of each rail transit subsystem.

[0025] In one embodiment, the indicator types include safety type, efficiency type, and energy consumption type. The step of decomposing each set of rail transit management indicators according to preset decomposition rules further includes:

[0026] Determine the correlation between different sets of rail transit management indicators for the safety type, efficiency type, and energy consumption type;

[0027] Based on the aforementioned relationships and preset decomposition rules, each set of rail transit management indicators is decomposed.

[0028] Secondly, this application also provides an index processing device for a rail transit management system, wherein the rail transit management system communicates with multiple rail transit subsystems, and the device includes:

[0029] The acquisition module is used to acquire a set of rail transit management indicators of various indicator types in response to indicator processing requests;

[0030] The indicator decomposition module is used to decompose each set of rail transit management indicators according to preset decomposition rules to obtain the initial management indicators corresponding to each rail transit subsystem; wherein each initial management indicator includes multiple initial indicator values, and each initial indicator value has a corresponding indicator type and initial weight.

[0031] The indicator update module is used to acquire real-time rail transit data of each of the rail transit subsystems, adjust the initial indicator values ​​and initial weights of each of the initial indicators according to the real-time rail transit data, so as to update each of the initial management indicators and obtain the target management indicators.

[0032] The instruction transmission module is used to convert each of the target management indicators into corresponding rail transit control and scheduling instructions, and to transmit each of the rail transit control and scheduling instructions to the corresponding rail transit subsystem; wherein, the rail transit control and scheduling instructions are used by the rail transit subsystem to achieve the target management indicators.

[0033] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0034] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0035] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described above.

[0036] The aforementioned rail transit management system's indicator processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product, in response to indicator processing requests, acquire rail transit management indicator sets of various indicator types, decompose each rail transit management indicator set according to preset decomposition rules, obtain initial management indicators corresponding to each rail transit subsystem, each initial management indicator includes multiple initial indicator values, each initial indicator value has a corresponding indicator type and initial weight, acquire real-time rail transit data of each rail transit subsystem, adjust each initial indicator value and each initial weight according to the real-time rail transit data to update each initial management indicator, obtain target management indicators, convert each target management indicator into corresponding rail transit control and scheduling instructions, and transmit each rail transit control and scheduling instruction to the corresponding rail transit subsystem, realizing a complete "monitoring-analysis-decision-execution-feedback" link, adapting to complex and ever-changing rail transit operating environments, converting management indicators into executable rail transit control and scheduling instructions, significantly improving rail transit management efficiency, and significantly enhancing the real-time performance and accuracy of rail transit indicator management. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram of the application environment provided in an embodiment of this application;

[0039] Figure 2 A flowchart illustrating the steps of an index processing method for a rail transit management system provided in an embodiment of this application;

[0040] Figure 3 A system architecture diagram of a rail transit indicator processing system provided in an embodiment of this application;

[0041] Figure 4 A structural block diagram of an index processing device for a rail transit management system provided in an embodiment of this application;

[0042] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0044] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0045] The index processing method for the rail transit management system provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Terminal 102 initiates an indicator processing request. Server 104 responds to the request by obtaining a set of rail transit management indicators of various indicator types. Server 104 decomposes each set of rail transit management indicators according to preset decomposition rules to obtain initial management indicators corresponding to each rail transit subsystem. Each initial management indicator includes multiple initial indicator values, each with a corresponding indicator type and initial weight. Server 104 obtains real-time rail transit data from each rail transit subsystem, adjusts each initial indicator value and initial weight based on the real-time rail transit data to update each initial management indicator, obtaining the target management indicator. Server 104 converts each target management indicator into corresponding rail transit control and scheduling instructions, and transmits each rail transit control and scheduling instruction to the corresponding rail transit subsystem. The rail transit control and scheduling instructions are used by the rail transit subsystem to achieve the target management indicator. Server 104 returns the indicator processing result to terminal 102. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, etc. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0046] In one exemplary embodiment, such as Figure 2 As shown, a method for processing indicators in a rail transit management system is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 202 to 208. Wherein:

[0047] Step 202: In response to the indicator processing request, obtain a set of rail transit management indicators of various indicator types;

[0048] Indicator types can include safety type, efficiency type, energy consumption type, reliability type, etc.; among them, safety type indicators are used to assess the system's ability to withstand risks and ensure the safety of personnel and operations; efficiency type indicators are used to measure the resource utilization of the transportation system and the timeliness of completing rail transit operation tasks; energy consumption type indicators are used to monitor energy consumption levels to support energy conservation and cost control; reliability type indicators are used to evaluate the performance of the system and equipment in continuous and stable operation and reducing interruptions.

[0049] In a practical implementation, the rail transit management indicator set can contain structured storage of the metadata of the rail transit management indicators. The metadata can specifically include indicator codes, calculation logic, associated parameter sets, weight coefficient ranges, etc.

[0050] Step 204: Decompose each set of rail transit management indicators according to the preset decomposition rules to obtain the initial management indicators corresponding to each rail transit subsystem; wherein, each initial management indicator includes multiple initial indicator values, and each initial indicator value has a corresponding indicator type and initial weight.

[0051] In practical implementation, decomposition rules can be pre-determined based on the basic information of each rail transit subsystem, such as line information, equipment configuration information, and historical passenger flow information. These rules are then used to decompose the set of rail transit management indicators for each subsystem, resulting in initial management indicators for each subsystem. Each initial management indicator comprises multiple initial indicator values, each with a corresponding indicator type and initial weight. The initial weight characterizes the importance of each initial indicator value within the overall initial management indicators.

[0052] For example, the safety-type rail transit management indicator set includes equipment failure rate, with a global indicator value configured as 1%; the efficiency-type rail transit management indicator set includes punctuality rate, with a global indicator value configured as 98%. There are existing rail transit subsystems corresponding to stations A and B. Station A has older equipment than station B, station B has a higher historical passenger flow than station A, and most of the lines associated with station A are located in rugged mountainous areas prone to accidents. Based on this basic information, corresponding decomposition rules are generated to initially decompose the rail transit management indicators. The initial management indicators for station A are: initial equipment failure rate of 1.3% with an initial weight of 0.7, and initial punctuality rate of 99% with an initial weight of 0.3; the initial management indicators for station B are: initial equipment failure rate of 0.7% with an initial weight of 0.6, and initial punctuality rate of 97% with an initial weight of 0.4.

[0053] In some embodiments, each initial indicator value also has a corresponding indicator level, which includes a track line level, a station level, and a job level. The decomposition of each rail transit management indicator set according to a preset decomposition rule includes:

[0054] According to the preset spatiotemporal dimension decomposition rules, each set of rail transit management indicators is decomposed into the initial indicator values ​​of the rail line level of each rail transit subsystem.

[0055] According to the preset equipment association decomposition rules, the initial index values ​​of each track line level are decomposed into the initial index values ​​of each station level of each rail transit subsystem.

[0056] According to the preset job mapping decomposition rules, the initial index values ​​of each station level are decomposed into the initial index values ​​of each job level of each rail transit subsystem.

[0057] In practical implementation, the line level refers to rail transit management indicators based on the line as the basic unit, which can adapt to the passenger flow characteristics and operational needs of different lines; the station level refers to rail transit management indicators based on the stations associated with each line as the basic unit, by refining the indicator level to the station level, and allocating rail transit management indicators in a differentiated manner based on the station size and functional positioning; the job level refers to decomposing rail transit management indicators to the specific personnel corresponding to each job based on the job associated with each station as the basic unit.

[0058] According to the preset spatiotemporal dimension decomposition rules, such as the decomposition rules corresponding to the distribution location of the entire rail transit network, holiday characteristics, and seasonal characteristics, the initial index values ​​of each rail line level are decomposed into the initial index values ​​of each rail transit subsystem at the station level. Furthermore, according to the equipment association decomposition rules, such as the decomposition rules corresponding to the association relationship between station functions and equipment configuration, the initial index values ​​of each rail line level are decomposed into the initial index values ​​of each rail transit subsystem at the station level. Furthermore, according to the job mapping decomposition rules, such as the decomposition rules corresponding to job responsibilities, operating procedures, and process nodes, the initial index values ​​of each station level are decomposed into the initial index values ​​of each rail transit subsystem at the job level.

[0059] In some embodiments, the indicator types include safety type, efficiency type, and energy consumption type, and the step of decomposing each set of rail transit management indicators according to preset decomposition rules further includes:

[0060] Determine the correlation between different sets of rail transit management indicators for the safety type, efficiency type, and energy consumption type;

[0061] Based on the aforementioned relationships and preset decomposition rules, each set of rail transit management indicators is decomposed.

[0062] In practical implementation, the set of rail transit management indicators for safety type can include indicators such as equipment failure rate, emergency response timeliness, and inspection completion rate; the set of rail transit management indicators for efficiency type can include indicators such as train punctuality rate, passenger dwell time, and gate throughput rate; and the set of rail transit management indicators for energy consumption type can include indicators such as traction energy consumption coefficient, lighting energy consumption ratio, and air conditioning energy efficiency.

[0063] By constructing a parameter correlation matrix, the correlation between different sets of rail transit management indicators of safety type, efficiency type, and energy consumption type is characterized.

[0064] Taking the parameter correlation matrix between different indicator values ​​in a rail transit management indicator set of the same type as an example, the parameter correlation matrix for safety type can correlate equipment reliability (such as failure rate) with emergency response capability (such as response time); the parameter correlation matrix for efficiency type can correlate train operation efficiency (such as punctuality rate) with passenger service efficiency (such as dwell time); and the parameter correlation matrix for energy consumption type can correlate the energy consumption of subsystems such as traction and lighting. By establishing parameter correlation matrices, dynamic impact analysis between indicators can be achieved, such as calculating the transmission effect of changes in train punctuality rate on energy consumption indicators, providing data support for the decomposition of rail transit management indicator sets.

[0065] Furthermore, based on the correlation between different rail transit management indicator sets of safety type, efficiency type, and energy consumption type, and the preset decomposition rules, the initial management indicators of each rail transit subsystem are determined for preliminary indicator decomposition.

[0066] Step 206: Obtain real-time rail transit data for each of the rail transit subsystems, and adjust the initial index values ​​and initial weights according to the real-time rail transit data to update the initial management indicators and obtain the target management indicators.

[0067] In practical implementation, by extracting data features from real-time rail transit data, the real-time operation of each rail transit subsystem can be reflected. Then, the initial indicator values ​​and initial weights of each rail transit subsystem can be dynamically adjusted in real time to obtain target management indicators.

[0068] For example, the initial indicator values ​​and initial weights of a certain rail transit subsystem are "average passenger entry time ≤ 2 minutes, weight 0.15" and "security check equipment activation rate ≥ 99%, weight 0.85". If the real-time rail transit data reflects the detection of a suspected security threat, the initial indicator values ​​and initial weights are adjusted to "security check equipment activation rate = 100%, weight 0.45" and "average passenger entry time ≤ 2.5 minutes, weight 0.55" to ensure the security of the stations corresponding to the rail transit subsystem.

[0069] In practical applications, distributed data acquisition nodes can be deployed in various rail transit subsystems, such as station servers, on-board terminals, and equipment controllers in the rail transit subsystems. These distributed data acquisition nodes collect real-time rail transit data from each rail transit subsystem and transmit it through the corresponding data interfaces.

[0070] The distributed data acquisition nodes can be equipped with a data integrity verification mechanism. When the data missing rate exceeds 15% (or other user-defined values), a data re-acquisition process is triggered. The data cleaning unit is configured with an abnormal data identification rule base. The distributed acquisition nodes set timestamp verification and data packet verification codes in the data cache area. When data is missing, it is supplemented based on historical data interpolation to ensure data continuity.

[0071] In some embodiments, real-time rail transit data can also be cleaned by caching the transmitted real-time rail transit data in a data buffer and then cleaning the real-time rail transit data of different priorities in a priority queue.

[0072] During the data cleaning process, real-time rail transit data can also be verified through an anomaly identification rule base. The anomaly identification rule base includes rules such as numerical range verification (e.g., marking an anomaly when passenger flow > 200% of design capacity) and mutation detection (triggering a review when fluctuations in adjacent cycles exceed 30%), which improves data credibility.

[0073] In some embodiments, adjusting the initial index values ​​and initial weights based on the real-time rail transit data includes:

[0074] Adjust the initial index values ​​according to the differences between the real-time rail transit data and the corresponding preset thresholds;

[0075] The system state of each rail transit subsystem is determined based on the real-time rail transit data, and a target weight matching the system state is determined.

[0076] The initial weights are adjusted using the target weights.

[0077] In practical implementation, real-time rail transit data can be data transmitted in real time by the rail transit subsystem, such as passenger flow, real-time train location, speed, status and energy consumption of key equipment in traction substations / step-down substations, etc. The preset threshold can be the threshold under normal conditions corresponding to each type of real-time rail transit data. The initial index value is adjusted according to the difference between the real-time rail transit data and the corresponding preset threshold.

[0078] For example, the initial target value for the "traction energy consumption" of a certain rail transit subsystem is "≤3.5kWh / vehicle-kilometer". If real-time rail transit data shows that the average real-time traction energy consumption continuously exceeds a preset threshold (e.g., 3.8kWh / vehicle-kilometer) due to severe weather (e.g., strong winds) during a certain period, the initial target value will be adjusted to "≤3.7kWh / vehicle-kilometer" to adapt to the increase in basic energy consumption caused by changes in severe environment.

[0079] In the specific implementation, the system status of each rail transit subsystem is determined based on real-time rail transit data. This system status can reflect the current operating state of the rail transit subsystem, such as normal operation, negative pressure operation, light load operation, etc. Target weights matching each system status are determined based on the system status, and the initial weights are adjusted using the target weights, such as by direct replacement or averaging.

[0080] For example, a certain rail transit subsystem is a station control system. Real-time rail transit data indicates that the passenger density on the station platform continuously exceeds a preset threshold (e.g., 2.5 people / square meter), determining the system state of the station control system as "high passenger flow control state". Weights are assigned to safety-related indicators such as "platform clearing efficiency" and "escalator emergency stop response time" with higher weights, while weights are assigned to other types of indicators with lower weights, resulting in target weights that match the system state. The initial weights are then adjusted based on these target weights.

[0081] In practical applications, the threshold range corresponding to the preset threshold can be dynamically adjusted, such as automatically correcting the threshold range based on historical data trends. Another example is the automatic expansion of the threshold range based on seasonal factors (such as increased air conditioning energy consumption benchmarks in summer) or operational phases (such as the transition period after the opening of a new line).

[0082] In some embodiments, adjusting the initial index values ​​based on the difference between each of the real-time rail transit data and the corresponding preset threshold includes:

[0083] If the current time meets the time corresponding to the preset index adjustment cycle, determine the first difference between each of the real-time rail transit data and the corresponding preset threshold.

[0084] If the first difference does not meet the corresponding preset conditions, the initial index value of the corresponding rail transit subsystem is adjusted according to the first difference.

[0085] In the event of an abnormal event in any of the rail transit subsystems, a second difference is determined between the real-time rail transit data of the rail transit subsystem in which the abnormal event occurred and the corresponding preset threshold.

[0086] If the second difference does not meet the corresponding preset conditions, the initial index value of the rail transit subsystem that experienced the abnormal event is adjusted according to the second difference.

[0087] In practical implementation, the preset indicator adjustment cycle can be every half hour, every hour, etc., to periodically correct the initial indicator values. If the first difference does not meet the corresponding preset conditions, the initial indicator value of the corresponding rail transit subsystem is adjusted according to the first difference. For example, if the difference between real-time rail transit data and a preset threshold does not meet the corresponding preset range, it indicates that the real-time rail transit data deviates from the normal state, and the initial indicator value is adjusted according to the actual degree of deviation represented by the difference.

[0088] If any rail transit subsystem experiences an abnormal event (such as a sudden event like a large passenger flow or equipment failure), the real-time rail transit data of the subsystem experiencing the abnormal event is verified. A second difference between the real-time rail transit data and a preset threshold is determined. If the second difference does not meet the corresponding preset conditions, it indicates that the impact of the abnormal event is severe, and the initial indicator values ​​need to be adjusted. Therefore, the initial indicator values ​​of the rail transit subsystem experiencing the abnormal event are adjusted according to the second difference to accommodate the interference caused by the abnormal event. For example, by analyzing the fluctuation trend of real-time rail transit data through a sliding time window, a fluctuation trend indicator value is obtained. When the difference between the fluctuation trend indicator value and the preset threshold does not meet the corresponding preset range, the initial indicator values ​​of the rail transit subsystem experiencing the abnormal event are adjusted according to this difference.

[0089] In some embodiments, determining the system state of each rail transit subsystem based on the real-time rail transit data and determining the target weight matching the system state includes:

[0090] Each system state is input into a pre-trained weight allocation reinforcement learning model, which maps each system state into a continuous action space. Based on each continuous action space, the target weights that match each system state are output.

[0091] In practical implementation, the system state can be represented by vectors, tensors, matrices, etc. For example, the system state can be input into a pre-trained weight allocation reinforcement learning model, which maps the system state into a continuous action space. Forward reasoning is performed with the optimal expectation of this continuous action space as the objective (e.g., optimizing excessive passenger dwell time) to output the optimal action vector, which includes the target weights corresponding to each initial index value.

[0092] For example, real-time rail transit data such as platform congestion, average train delay, and passenger flow intensity are combined into a vector. This vector can represent the system state of the rail transit subsystem as "high passenger load state". This vector is input into a weighted reinforcement learning model. The weighted reinforcement learning model maps the system state into a continuous action space. The model performs forward reasoning with the optimal expectation of the continuous action space, namely "improving station safety and reducing passenger pressure", and outputs the optimal action vector. The corresponding target weights can be: 0.75 for safety type, 0.2 for efficiency type, and 0.05 for energy consumption type.

[0093] Step 208: Convert each of the target management indicators into corresponding rail transit control and scheduling instructions, and transmit each of the rail transit control and scheduling instructions to the corresponding rail transit subsystem; wherein, the rail transit control and scheduling instructions are used by the rail transit subsystem to achieve the target management indicators.

[0094] Rail transit control and dispatch instructions can include specific equipment control instructions, personnel dispatch instructions, resource allocation instructions, etc., for the rail transit subsystem to execute or issue.

[0095] In practical implementation, target management indicators can be converted into corresponding rail transit control and scheduling instructions through preset mapping rules. Alternatively, target management indicators can be input into a pre-trained instruction generation model, which will then output the optimal rail transit control and scheduling instructions that achieve the target management indicators for the rail transit subsystem to execute, enabling the rail transit subsystem to achieve the corresponding target management indicators.

[0096] In practical applications, a multi-protocol converter (supporting mutual conversion between Modbus, IEC61850, TCP / IP, and other protocols) can be used to convert the communication protocol for transmitting rail transit control and dispatching instructions into the communication protocol used by the corresponding rail transit subsystem, enabling bidirectional data interaction between heterogeneous systems such as signal control systems, power supply systems, and environmental monitoring systems. Furthermore, priorities can be configured for rail transit control and dispatching instructions, for example, by setting the priorities of rail transit control and dispatching instructions to three levels: immediate execution, planned execution, and standby instructions, and managing them through an instruction queue to avoid overloading of the rail transit subsystem.

[0097] In some embodiments, a rail transit indicator processing system is also provided, such as Figure 3 As shown, it includes:

[0098] The indicator library construction module is configured with a rail transit operation indicator template library. The template library includes rail transit management indicator sets of safety type, efficiency type, and energy consumption type. Each rail transit management indicator set contains structured stored indicator metadata, which includes at least the indicator code, calculation logic, associated parameter set, and weight coefficient range. The indicator library construction module designs three core indicator sets of safety, efficiency, and energy consumption according to industry characteristics, and ensures the traceability and scalability of the indicators through structured metadata storage.

[0099] The intelligent decomposition engine connects to the indicator library construction module and is configured with a rule-driven decomposer and a machine learning optimizer. The rule-driven decomposer has a built-in rail transit operation decomposition rule library, which includes spatiotemporal dimension decomposition rules, equipment association rules, and job mapping rules. The machine learning optimizer integrates a weight allocation reinforcement learning model, which is used to dynamically determine the target weights of indicator values. The intelligent decomposition engine adopts a rule-based and machine learning fusion mechanism. The rule-driven decomposer performs preliminary decomposition of the rail transit management indicator set based on preset business rules such as spatiotemporal dimensions and equipment associations. The weight allocation reinforcement learning model dynamically optimizes the weight allocation, solving the problem of insufficient adaptability of the traditional fixed weight mode in sudden scenarios.

[0100] The dynamic adjustment module is equipped with a real-time data interface and an indicator calibrator. The real-time data interface connects to the AFC (Automatic Fare Collection) system, signaling system, and power monitoring system, and is used to acquire passenger flow data, train location data, and energy consumption data in real time. The indicator calibrator is equipped with an anomaly detection algorithm and an adaptive adjustment strategy. The dynamic adjustment module accesses the data streams of multiple business systems through the real-time data interface, and combined with the anomaly detection algorithm of the indicator calibrator, it can achieve minute-level dynamic correction of indicators.

[0101] The instruction generation module includes an executable instruction conversion unit and an instruction verification unit. The executable instruction conversion unit converts target management indicators into equipment control instructions, personnel scheduling instructions, and resource configuration instructions. The instruction generation module converts optimized indicator parameters into executable equipment control and resource scheduling instructions. Through multi-protocol conversion and priority management by the interface adaptation module, the instructions are accurately delivered to each subsystem.

[0102] The interface adapter module includes a multi-protocol converter and an instruction distribution controller. The interface adapter module supports bidirectional data interaction with signal control systems, power supply systems, and environmental monitoring systems.

[0103] The data acquisition module includes distributed data acquisition nodes and a data cleaning unit. The distributed data acquisition nodes are deployed on the station server, on-board terminal, and equipment controller. The data cleaning unit is equipped with a data cache and a priority queue. The data acquisition module ensures data quality through distributed nodes and data cleaning mechanisms. The early warning feedback module enables rapid anomaly location through multi-level threshold early warning and intelligent diagnosis. The visualization monitoring module provides intuitive operational decision support.

[0104] The early warning feedback module includes a multi-level threshold early warning device and an intelligent diagnostic unit. The early warning device is set with differentiated threshold ranges, including regular threshold, early warning threshold, and emergency threshold.

[0105] The multi-level threshold early warning system employs a dynamic threshold adjustment algorithm that automatically corrects the threshold range based on historical data trends. The intelligent diagnostic unit incorporates a fault correlation analysis model capable of identifying abnormal correlation patterns among multiple indicators. For example, during the implementation of this solution, the dynamic threshold adjustment algorithm automatically expands the threshold range based on seasonal factors (such as increased air conditioning energy consumption benchmarks in summer) and operational phases (such as the transition period after a new line opens), avoiding false alarms. The correlation analysis model of the intelligent diagnostic unit can identify abnormal patterns among multiple indicators, such as the correlation analysis between train delays and gate congestion, assisting in locating the root cause.

[0106] The visualization monitoring module includes a 3D situation display unit and an interactive control interface. The 3D situation display unit integrates GIS maps, equipment topology diagrams, and indicator trend curves.

[0107] The 3D situation display unit supports multi-dimensional data overlay display, including real-time video streams, equipment status data, and indicator completion heatmaps. The interactive control interface provides command simulation execution functionality. The 3D situation display unit uses layered rendering technology to overlay real-time video, equipment status heatmaps, and other multi-dimensional data, supporting view zooming and profile analysis. The interactive control interface allows administrators to simulate the effects of command issuance (such as passenger flow forecasting after adjusting departure intervals), reducing practical operational risks.

[0108] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0109] Based on the same inventive concept, this application also provides an index processing device for a rail transit management system to implement the index processing method of the rail transit management system described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the index processing device for a rail transit management system provided below can be found in the limitations of the index processing method for the rail transit management system described above, and will not be repeated here.

[0110] In one exemplary embodiment, such as Figure 4 As shown, a signal processing device 40 for a rail transit management system is provided, comprising:

[0111] The acquisition module 401 is used to acquire a set of rail transit management indicators of various indicator types in response to the indicator processing request;

[0112] The indicator decomposition module 402 is used to decompose each set of rail transit management indicators according to a preset decomposition rule to obtain the initial management indicators corresponding to each rail transit subsystem; wherein each initial management indicator includes multiple initial indicator values, and each initial indicator value has a corresponding indicator type and initial weight.

[0113] The indicator update module 403 is used to acquire real-time rail transit data of each of the rail transit subsystems, adjust the initial indicator values ​​and initial weights of each of the initial indicators according to the real-time rail transit data, so as to update each of the initial management indicators and obtain the target management indicators.

[0114] The instruction transmission module 404 is used to convert each of the target management indicators into corresponding rail transit control and scheduling instructions, and to transmit each of the rail transit control and scheduling instructions to the corresponding rail transit subsystem; wherein, the rail transit control and scheduling instructions are used by the rail transit subsystem to achieve the target management indicators.

[0115] In one embodiment, adjusting the initial index values ​​and initial weights based on the real-time rail transit data includes:

[0116] Adjust the initial index values ​​according to the differences between the real-time rail transit data and the corresponding preset thresholds;

[0117] The system state of each rail transit subsystem is determined based on the real-time rail transit data, and a target weight matching the system state is determined.

[0118] The initial weights are adjusted using the target weights.

[0119] In one embodiment, adjusting the initial index values ​​based on the difference between each of the real-time rail transit data and the corresponding preset threshold includes:

[0120] If the current time meets the time corresponding to the preset index adjustment cycle, determine the first difference between each of the real-time rail transit data and the corresponding preset threshold.

[0121] If the first difference does not meet the corresponding preset conditions, the initial index value of the corresponding rail transit subsystem is adjusted according to the first difference.

[0122] In the event of an abnormal event in any of the rail transit subsystems, a second difference is determined between the real-time rail transit data of the rail transit subsystem in which the abnormal event occurred and the corresponding preset threshold.

[0123] If the second difference does not meet the corresponding preset conditions, the initial index value of the rail transit subsystem that experienced the abnormal event is adjusted according to the second difference.

[0124] In one embodiment, determining the system state of each rail transit subsystem based on the real-time rail transit data, and determining the target weight matching the system state, includes:

[0125] Each system state is input into a pre-trained weight allocation reinforcement learning model, which maps each system state into a continuous action space. Based on each continuous action space, the target weights that match each system state are output.

[0126] In one embodiment, each of the initial indicator values ​​also has a corresponding indicator level, which includes a track line level, a station level, and a job level. The decomposition of each set of rail transit management indicators according to a preset decomposition rule includes:

[0127] According to the preset spatiotemporal dimension decomposition rules, each set of rail transit management indicators is decomposed into the initial indicator values ​​of the rail line level of each rail transit subsystem.

[0128] According to the preset equipment association decomposition rules, the initial index values ​​of each track line level are decomposed into the initial index values ​​of each station level of each rail transit subsystem.

[0129] According to the preset job mapping decomposition rules, the initial index values ​​of each station level are decomposed into the initial index values ​​of each job level of each rail transit subsystem.

[0130] In one embodiment, the indicator types include safety type, efficiency type, and energy consumption type. The step of decomposing each set of rail transit management indicators according to preset decomposition rules further includes:

[0131] Determine the correlation between different sets of rail transit management indicators for the safety type, efficiency type, and energy consumption type;

[0132] Based on the aforementioned relationships and preset decomposition rules, each set of rail transit management indicators is decomposed.

[0133] Each module in the indicator processing device of the aforementioned rail transit management system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0134] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data including, but not limited to, sets of rail transit management indicators. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for processing indicators in a rail transit management system.

[0135] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0136] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described index processing method for a rail transit management system.

[0137] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described indicator processing method for a rail transit management system.

[0138] In one embodiment, when the computer program is executed by a processor, it also implements the above-described index processing method for the rail transit management system.

[0139] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described indicator processing method for a rail transit management system.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0141] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0142] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0143] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for processing indicators in a rail transit management system, characterized in that, The rail transit management system communicates with multiple rail transit subsystems, and the method includes: In response to indicator processing requests, obtain a set of rail transit management indicators of various indicator types; According to the preset decomposition rules, each set of rail transit management indicators is decomposed to obtain the initial management indicators corresponding to each rail transit subsystem; wherein, each initial management indicator includes multiple initial indicator values, and each initial indicator value has a corresponding indicator type and initial weight. Real-time rail transit data of each of the rail transit subsystems is obtained, and the initial index values ​​and initial weights of each of the initial indicators are adjusted according to the real-time rail transit data to update the initial management indicators and obtain the target management indicators. Each of the target management indicators is converted into a corresponding rail transit control and scheduling instruction, and each of the rail transit control and scheduling instructions is transmitted to the corresponding rail transit subsystem; wherein, the rail transit control and scheduling instructions are used by the rail transit subsystem to achieve the target management indicators.

2. The method according to claim 1, characterized in that, The step of adjusting the initial index values ​​and initial weights based on the real-time rail transit data includes: Adjust the initial index values ​​according to the differences between the real-time rail transit data and the corresponding preset thresholds; The system state of each rail transit subsystem is determined based on the real-time rail transit data, and a target weight matching the system state is determined. The initial weights are adjusted using the target weights.

3. The method according to claim 2, characterized in that, The step of adjusting the initial index values ​​based on the differences between the real-time rail transit data and the corresponding preset thresholds includes: If the current time meets the time corresponding to the preset index adjustment cycle, determine the first difference between each of the real-time rail transit data and the corresponding preset threshold. If the first difference does not meet the corresponding preset conditions, the initial index value of the corresponding rail transit subsystem is adjusted according to the first difference. In the event of an abnormal event in any of the rail transit subsystems, a second difference is determined between the real-time rail transit data of the rail transit subsystem in which the abnormal event occurred and the corresponding preset threshold. If the second difference does not meet the corresponding preset conditions, the initial index value of the rail transit subsystem that experienced the abnormal event is adjusted according to the second difference.

4. The method according to claim 2, characterized in that, The step of determining the system state of each rail transit subsystem based on the real-time rail transit data, and determining the target weight matching the system state, includes: Each system state is input into a pre-trained weight allocation reinforcement learning model, which maps each system state into a continuous action space. Based on each continuous action space, the target weights that match each system state are output.

5. The method according to any one of claims 1 to 4, characterized in that, Each of the initial indicator values ​​also has a corresponding indicator level, which includes the track line level, station level, and job level. The decomposition of each set of rail transit management indicators according to preset decomposition rules includes: According to the preset spatiotemporal dimension decomposition rules, each set of rail transit management indicators is decomposed into the initial indicator values ​​of the rail line level of each rail transit subsystem. According to the preset equipment association decomposition rules, the initial index values ​​of each track line level are decomposed into the initial index values ​​of each station level of each rail transit subsystem. According to the preset job mapping decomposition rules, the initial index values ​​of each station level are decomposed into the initial index values ​​of each job level of each rail transit subsystem.

6. The method according to any one of claims 1 to 4, characterized in that, The indicator types include safety type, efficiency type, and energy consumption type. The step of decomposing each set of rail transit management indicators according to preset decomposition rules also includes: Determine the correlation between different sets of rail transit management indicators for the safety type, efficiency type, and energy consumption type; Based on the aforementioned relationships and preset decomposition rules, each set of rail transit management indicators is decomposed.

7. An index processing device for a rail transit management system, characterized in that, The rail transit management system communicates with multiple rail transit subsystems, and the device includes: The acquisition module is used to acquire a set of rail transit management indicators of various indicator types in response to indicator processing requests; The indicator decomposition module is used to decompose each set of rail transit management indicators according to preset decomposition rules to obtain the initial management indicators corresponding to each rail transit subsystem; wherein each initial management indicator includes multiple initial indicator values, and each initial indicator value has a corresponding indicator type and initial weight. The indicator update module is used to acquire real-time rail transit data of each of the rail transit subsystems, adjust the initial indicator values ​​and initial weights of each of the initial indicators according to the real-time rail transit data, so as to update each of the initial management indicators and obtain the target management indicators. The instruction transmission module is used to convert each of the target management indicators into corresponding rail transit control and scheduling instructions, and to transmit each of the rail transit control and scheduling instructions to the corresponding rail transit subsystem; wherein, the rail transit control and scheduling instructions are used by the rail transit subsystem to achieve the target management indicators.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images